Haris Vikalo

Dongjun Kim, Adrian de Wynter, Huancheng Chen et al.

While finetuning effectively adapts foundation models to specialized downstream tasks, it can degrade nontarget capabilities acquired during pretraining. Existing forgetting aware methods typically seek safer updates through specialized initialization or fixed constraints, but do not regulate the adaptation preservation trade-off during training. We propose Foundation Preserving LoRA (FoLoRA), a forgetting aware optimization framework. Guided by a first order preservation condition, FoLoRA defines a forgetting penalty over pretraining-proxy activations and a task utility over downstream task activations. It then scores update directions by task utility per unit forgetting penalty via a generalized Rayleigh quotient. The resulting spectral coordinate system enables direction wise gated Adam updates, attenuating low utility to penalty directions during training. To estimate the forgetting penalty, FoLoRA constructs pretraining proxy calibration data by sampling from the pretrained model rather than relying on a single proxy dataset. Experiments on math, code, and instruction following adaptation show that FoLoRA achieves the strongest preservation adaptation balance over baselines, improving target task performance with best aggregate preservation of non target capabilities.

Abolfazl Hashemi, Mahsa Ghasemi, Haris Vikalo et al.

We study the problem of scheduling sensors in a resource-constrained linear dynamical system, where the objective is to select a small subset of sensors from a large network to perform the state estimation task. We formulate this problem as the maximization of a monotone set function under a matroid constraint. We propose a randomized greedy algorithm that is significantly faster than state-of-the-art methods. By introducing the notion of curvature which quantifies how close a function is to being submodular, we analyze the performance of the proposed algorithm and find a bound on the expected mean square error (MSE) of the estimator that uses the selected sensors in terms of the optimal MSE. Moreover, we derive a probabilistic bound on the curvature for the scenario where{\color{black}{ the measurements are i.i.d. random vectors with bounded $\ell_2$ norm.}} Simulation results demonstrate efficacy of the randomized greedy algorithm in a comparison with greedy and semidefinite programming relaxation methods.

Monica Ribero, Haris Vikalo, Gustavo De Veciana

Federated learning systems facilitate training of global models in settings where potentially heterogeneous data is distributed across a large number of clients. Such systems operate in settings with intermittent client availability and/or time-varying communication constraints. As a result, the global models trained by federated learning systems may be biased towards clients with higher availability. We propose F3AST, an unbiased algorithm that dynamically learns an availability-dependent client selection strategy which asymptotically minimizes the impact of client-sampling variance on the global model convergence, enhancing performance of federated learning. The proposed algorithm is tested in a variety of settings for intermittently available clients under communication constraints, and its efficacy demonstrated on synthetic data and realistically federated benchmarking experiments using CIFAR100 and Shakespeare datasets. We show up to 186% and 8% accuracy improvements over FedAvg, and 8% and 7% over FedAdam on CIFAR100 and Shakespeare, respectively.

Huancheng Chen, Johnny, Wang et al.

Heterogeneity of data distributed across clients limits the performance of global models trained through federated learning, especially in the settings with highly imbalanced class distributions of local datasets. In recent years, personalized federated learning (pFL) has emerged as a potential solution to the challenges presented by heterogeneous data. However, existing pFL methods typically enhance performance of local models at the expense of the global model's accuracy. We propose FedHKD (Federated Hyper-Knowledge Distillation), a novel FL algorithm in which clients rely on knowledge distillation (KD) to train local models. In particular, each client extracts and sends to the server the means of local data representations and the corresponding soft predictions -- information that we refer to as ``hyper-knowledge". The server aggregates this information and broadcasts it to the clients in support of local training. Notably, unlike other KD-based pFL methods, FedHKD does not rely on a public dataset nor it deploys a generative model at the server. We analyze convergence of FedHKD and conduct extensive experiments on visual datasets in a variety of scenarios, demonstrating that FedHKD provides significant improvement in both personalized as well as global model performance compared to state-of-the-art FL methods designed for heterogeneous data settings.

Huancheng Chen, Haris Vikalo

While federated learning (FL) systems often utilize quantization to battle communication and computational bottlenecks, they have heretofore been limited to deploying fixed-precision quantization schemes. Meanwhile, the concept of mixed-precision quantization (MPQ), where different layers of a deep learning model are assigned varying bit-width, remains unexplored in the FL settings. We present a novel FL algorithm, FedMPQ, which introduces mixed-precision quantization to resource-heterogeneous FL systems. Specifically, local models, quantized so as to satisfy bit-width constraint, are trained by optimizing an objective function that includes a regularization term which promotes reduction of precision in some of the layers without significant performance degradation. The server collects local model updates, de-quantizes them into full-precision models, and then aggregates them into a global model. To initialize the next round of local training, the server relies on the information learned in the previous training round to customize bit-width assignments of the models delivered to different clients. In extensive benchmarking experiments on several model architectures and different datasets in both iid and non-iid settings, FedMPQ outperformed the baseline FL schemes that utilize fixed-precision quantization while incurring only a minor computational overhead on the participating devices.

Huancheng Chen, Haris Vikalo

Federated learning (FL) is a privacy-promoting framework that enables potentially large number of clients to collaboratively train machine learning models. In a FL system, a server coordinates the collaboration by collecting and aggregating clients' model updates while the clients' data remains local and private. A major challenge in federated learning arises when the local data is heterogeneous -- the setting in which performance of the learned global model may deteriorate significantly compared to the scenario where the data is identically distributed across the clients. In this paper we propose FedDPMS (Federated Differentially Private Means Sharing), an FL algorithm in which clients deploy variational auto-encoders to augment local datasets with data synthesized using differentially private means of latent data representations communicated by a trusted server. Such augmentation ameliorates effects of data heterogeneity across the clients without compromising privacy. Our experiments on deep image classification tasks demonstrate that FedDPMS outperforms competing state-of-the-art FL methods specifically designed for heterogeneous data settings.

Madhumitha Sakthi, Ahmed Tewfik, Marius Arvinte et al.

Automotive radar has increasingly attracted attention due to growing interest in autonomous driving technologies. Acquiring situational awareness using multimodal data collected at high sampling rates by various sensing devices including cameras, LiDAR, and radar requires considerable power, memory and compute resources which are often limited at an edge device. In this paper, we present a novel adaptive radar sub-sampling algorithm designed to identify regions that require more detailed/accurate reconstruction based on prior environmental conditions' knowledge, enabling near-optimal performance at considerably lower effective sampling rates. Designed to robustly perform under variable weather conditions, the algorithm was shown on the Oxford raw radar and RADIATE dataset to achieve accurate reconstruction utilizing only 10% of the original samples in good weather and 20% in extreme (snow, fog) weather conditions. A further modification of the algorithm incorporates object motion to enable reliable identification of important regions. This includes monitoring possible future occlusions caused by objects detected in the present frame. Finally, we train a YOLO network on the RADIATE dataset to perform object detection directly on RADAR data and obtain a 6.6% AP50 improvement over the baseline Faster R-CNN network.

Jianing Zhu, Yeonju Ro, John Robertson et al.

Long-lived AI agents are increasingly deployed as persistent operational systems, yet they are still evaluated like freshly initialized models. Day-one benchmarks miss a basic systems question: how long does an agent remain reliable after deployment? Even when model weights are frozen, an agent's effective state keeps changing as it compresses interaction history, retrieves from a growing memory store, revises facts after updates, and undergoes routine maintenance. Reliability therefore becomes a lifespan property of the full agent harness, not only a snapshot property of the base model. We introduce AgingBench, a longitudinal reliability benchmark for agent lifespan engineering: measuring not only whether deployed agents degrade, but what form the degradation takes and where repair should target. AgingBench organizes agent aging into four mechanisms: compression aging, interference aging, revision aging, and maintenance aging. To diagnose these failures, AgingBench uses temporal dependency graphs and paired counterfactual probes that produce diagnostic profiles for the write, retrieval, and utilization stages of the memory pipeline. Across 7 scenarios, 14 models, multiple memory policies, and both runner-controlled and autonomous agents, over ~400 runs spanning 8 - 200 sessions show that agent aging is not one-dimensional: behavioral tests can remain clean while factual precision decays; derived-state tracking can collapse sharply within a single model; and the same wrong answer can require different repairs depending on what the diagnostic profile points to. These results suggest that reliable agent deployment requires lifespan evaluation, mechanism-level diagnosis, and stage-targeted repair, not only stronger day-one models.

Huancheng Chen, Haris Vikalo

Statistical heterogeneity of data present at client devices in a federated learning (FL) system renders the training of a global model in such systems difficult. Particularly challenging are the settings where due to communication resource constraints only a small fraction of clients can participate in any given round of FL. Recent approaches to training a global model in FL systems with non-IID data have focused on developing client selection methods that aim to sample clients with more informative updates of the model. However, existing client selection techniques either introduce significant computation overhead or perform well only in the scenarios where clients have data with similar heterogeneity profiles. In this paper, we propose HiCS-FL (Federated Learning via Hierarchical Clustered Sampling), a novel client selection method in which the server estimates statistical heterogeneity of a client's data using the client's update of the network's output layer and relies on this information to cluster and sample the clients. We analyze the ability of the proposed techniques to compare heterogeneity of different datasets, and characterize convergence of the training process that deploys the introduced client selection method. Extensive experimental results demonstrate that in non-IID settings HiCS-FL achieves faster convergence than state-of-the-art FL client selection schemes. Notably, HiCS-FL drastically reduces computation cost compared to existing selection schemes and is adaptable to different heterogeneity scenarios.

Haoran Zhang, Seohyeon Cha, Hasan Burhan Beytur et al.

Hierarchical inference systems route tasks across multiple computational layers, where each node may either finalize a prediction locally or offload the task to a node in the next layer for further processing. Learning optimal routing policies in such systems is challenging: inference loss is defined recursively across layers, while feedback on prediction error is revealed only at a terminal oracle layer. This induces a partial, policy-dependent feedback structure in which observability probabilities decay with depth, causing importance-weighted estimators to suffer from amplified variance. We study online routing for multi-layer hierarchical inference under long-term resource constraints and terminal-only feedback. We formalize the recursive loss structure and show that naive importance-weighted contextual bandit methods become unstable as feedback probability decays along the hierarchy. To address this, we develop a variance-reduced EXP4-based algorithm integrated with Lyapunov optimization, yielding unbiased loss estimation and stable learning under sparse and policy-dependent feedback. We provide regret guarantees relative to the best fixed routing policy in hindsight and establish near-optimality under stochastic arrivals and resource constraints. Experiments on large-scale multi-task workloads demonstrate improved stability and performance compared to standard importance-weighted approaches.

Seohyeon Cha, Huancheng Chen, Dongjun Kim et al.

Large language models (LLMs) deliver robust performance across diverse applications, yet their deployment often faces challenges due to the memory and latency costs of storing and accessing billions of parameters. Post-training quantization (PTQ) enables efficient inference by mapping pretrained weights to low-bit formats without retraining, but its effectiveness depends critically on both the quantization objective and the rounding procedure used to obtain low-bit weight representations. In this work, we show that interpolating between symmetric and asymmetric calibration acts as a form of regularization that preserves the standard quadratic structure used in PTQ while providing robustness to activation mismatch. Building on this perspective, we derive a simple successive rounding procedure that naturally incorporates asymmetric calibration, as well as a bounded-search extension that allows for an explicit trade-off between quantization quality and the compute cost. Experiments across multiple LLM families, quantization bit-widths, and benchmarks demonstrate that the proposed bounded search based on a regularized asymmetric calibration objective consistently improves perplexity and accuracy over PTQ baselines, while incurring only modest and controllable additional computational cost.

Shorya Consul, John Robertson, Haris Vikalo

It is estimated that approximately 15% of cancers worldwide can be linked to viral infections. The viruses that can cause or increase the risk of cancer include human papillomavirus, hepatitis B and C viruses, Epstein-Barr virus, and human immunodeficiency virus, to name a few. The computational analysis of the massive amounts of tumor DNA data, whose collection is enabled by the recent advancements in sequencing technologies, have allowed studies of the potential association between cancers and viral pathogens. However, the high diversity of oncoviral families makes reliable detection of viral DNA difficult and thus, renders such analysis challenging. In this paper, we introduce XVir, a data pipeline that relies on a transformer-based deep learning architecture to reliably identify viral DNA present in human tumors. In particular, XVir is trained on genomic sequencing reads from viral and human genomes and may be used with tumor sequence information to find evidence of viral DNA in human cancers. Results on semi-experimental data demonstrate that XVir is capable of achieving high detection accuracy, generally outperforming state-of-the-art competing methods while being more compact and less computationally demanding.

Madhumitha Sakthi, Ahmed Tewfik, Marius Arvinte et al.

Robust and accurate sensing is of critical importance for advancing autonomous automotive systems. The need to acquire situational awareness in complex urban conditions using sensors such as radar has motivated research on power and latency-efficient signal acquisition methods. In this paper, we present an end-to-end signal processing pipeline, capable of operating in extreme weather conditions, that relies on sub-sampled radar data to perform object detection in vehicular settings. The results of the object detection are further utilized to sub-sample forthcoming radar data, which stands in contrast to prior work where the sub-sampling relies on image information. We show robust detection based on radar data reconstructed using 20% of samples under extreme weather conditions such as snow or fog, and on low-illuminated nights. Additionally, we generate 20% sampled radar data in a fine-tuning set and show 1.1% gain in AP50 across scenes and 3% AP50 gain in motorway condition.

Sameer Bibikar, Haris Vikalo, Zhangyang Wang et al.

Federated learning (FL) enables distribution of machine learning workloads from the cloud to resource-limited edge devices. Unfortunately, current deep networks remain not only too compute-heavy for inference and training on edge devices, but also too large for communicating updates over bandwidth-constrained networks. In this paper, we develop, implement, and experimentally validate a novel FL framework termed Federated Dynamic Sparse Training (FedDST) by which complex neural networks can be deployed and trained with substantially improved efficiency in both on-device computation and in-network communication. At the core of FedDST is a dynamic process that extracts and trains sparse sub-networks from the target full network. With this scheme, "two birds are killed with one stone:" instead of full models, each client performs efficient training of its own sparse networks, and only sparse networks are transmitted between devices and the cloud. Furthermore, our results reveal that the dynamic sparsity during FL training more flexibly accommodates local heterogeneity in FL agents than the fixed, shared sparse masks. Moreover, dynamic sparsity naturally introduces an "in-time self-ensembling effect" into the training dynamics and improves the FL performance even over dense training. In a realistic and challenging non i.i.d. FL setting, FedDST consistently outperforms competing algorithms in our experiments: for instance, at any fixed upload data cap on non-iid CIFAR-10, it gains an impressive accuracy advantage of 10% over FedAvgM when given the same upload data cap; the accuracy gap remains 3% even when FedAvgM is given 2x the upload data cap, further demonstrating efficacy of FedDST. Code is available at: https://github.com/bibikar/feddst.

John T. Robertson, Jianing Zhu, Haris Vikalo et al.

Activation steering offers a lightweight way to control LLMs without retraining, but its effectiveness varies sharply across concepts. Prior work often reads this variability as evidence that many concepts are not captured by a single steering direction. We argue instead that much of it reflects search difficulty: a useful rank-1 intervention often exists, but finding it can be expensive. We formalize rank-1 steering as a budget-constrained optimization over intervention layer and coefficient. Across concepts and model families, prompt-boundary directional alignment predicts where effective interventions occur, enabling geometry-guided search that reaches high utility with substantially fewer evaluations, reducing the trials needed to recover 95\% of best-found utility by 39.8\% on average across three model families. To explain why some concepts remain expensive even under better search, we introduce \emph{concept granularity}, a measure of directional heterogeneity across contrastive contexts. Granularity distinguishes concepts whose difference vectors share a stable global direction from those where prompts agree locally within each input but the utility-maximizing direction rotates systematically across inputs. Higher granularity is associated with slower convergence and lower best-found performance (Pearson $r{=}0.44$ with trials-to-95\%, $r{=}{-}0.46$ with best-found utility, both $p<0.001$). We present \textit{GRACE}, a Granularity- and Representation-Aware Concept Engineering framework that uses activation geometry to diagnose the dominant source of steering difficulty, select the appropriate remedy, and allocate optimization effort efficiently. Our results shift the frame from ``\textit{when does rank-1 fail?}'' to ``\textit{when is rank-1 cheap and stable?}'', turning activation geometry from a descriptive tool into an actionable prior for LLM control.

Yiyue Chen, Haris Vikalo, Chianing Wang

Motivated by high resource costs of centralized machine learning schemes as well as data privacy concerns, federated learning (FL) emerged as an efficient alternative that relies on aggregating locally trained models rather than collecting clients' potentially private data. In practice, available resources and data distributions vary from one client to another, creating an inherent system heterogeneity that leads to deterioration of the performance of conventional FL algorithms. In this work, we present a federated quantization-based self-supervised learning scheme (Fed-QSSL) designed to address heterogeneity in FL systems. At clients' side, to tackle data heterogeneity we leverage distributed self-supervised learning while utilizing low-bit quantization to satisfy constraints imposed by local infrastructure and limited communication resources. At server's side, Fed-QSSL deploys de-quantization, weighted aggregation and re-quantization, ultimately creating models personalized to both data distribution as well as specific infrastructure of each client's device. We validated the proposed algorithm on real world datasets, demonstrating its efficacy, and theoretically analyzed impact of low-bit training on the convergence and robustness of the learned models.

Huancheng Chen, Haris Vikalo

Gradient inversion (GI) attacks present a threat to the privacy of clients in federated learning (FL) by aiming to enable reconstruction of the clients' data from communicated model updates. A number of such techniques attempts to accelerate data recovery by first reconstructing labels of the samples used in local training. However, existing label extraction methods make strong assumptions that typically do not hold in realistic FL settings. In this paper we present a novel label recovery scheme, Recovering Labels from Local Updates (RLU), which provides near-perfect accuracy when attacking untrained (most vulnerable) models. More significantly, RLU achieves high performance even in realistic real-world settings where the clients in an FL system run multiple local epochs, train on heterogeneous data, and deploy various optimizers to minimize different objective functions. Specifically, RLU estimates labels by solving a least-square problem that emerges from the analysis of the correlation between labels of the data points used in a training round and the resulting update of the output layer. The experimental results on several datasets, architectures, and data heterogeneity scenarios demonstrate that the proposed method consistently outperforms existing baselines, and helps improve quality of the reconstructed images in GI attacks in terms of both PSNR and LPIPS.

Usman Akram, Fan Zhang, Yang Li et al.

Accurate channel state information (CSI) is essential for reliable multiuser MIMO operation. In 5G NR, reciprocity-based beamforming via uplink Sounding Reference Signals (SRS) face resource and coverage constraints, motivating sparse non-uniform SRS allocation. Prior masked-autoencoder (MAE) approaches improve coverage but overfit to training masks and degrade under unseen distortions (e.g., additional masking, interference, clipping, non-Gaussian noise). We propose a diffusion-based channel inpainting framework that integrates system-model knowledge at inference via a likelihood-gradient term, enabling a single trained model to adapt across mismatched conditions. On standardized CDL channels, the score-based diffusion variant consistently outperforms a UNet score-model baseline and the one-step MAE under distribution shift, with improvements up to 14 dB NMSE in challenging settings (e.g., Laplace noise, user interference), while retaining competitive accuracy under matched conditions. These results demonstrate that diffusion-guided inpainting is a robust and generalizable approach for super-capacity SRS design in 5G NR systems.

Huancheng Chen, Jingtao Li, Weiming Zhuang et al.

Recently, many text-to-image diffusion models excel at generating high-resolution images from text but struggle with precise control over spatial composition and object counting. To address these challenges, prior works developed layout-to-image (L2I) approaches that incorporate layout instructions into text-to-image models. However, existing L2I methods typically require fine-tuning of pre-trained parameters or training additional control modules for the diffusion models. In this work, we propose a training-free L2I approach, MAC (Marginal Attention Constrained Generation), which eliminates the need for additional modules or fine-tuning. Specifically, we use text-visual cross-attention feature maps to quantify inconsistencies between the layout of the generated images and the provided instructions, and then compute loss functions to optimize latent features during the diffusion reverse process. To enhance spatial controllability and mitigate semantic failures in complex layout instructions, we leverage pixel-to-pixel correlations in the self-attention feature maps to align cross-attention maps and combine three loss functions constrained by boundary attention to update latent features. Comprehensive experimental results on both L2I and non-L2I pretrained diffusion models demonstrate that our method outperforms existing training-free L2I techniques both quantitatively and qualitatively in terms of image composition on the DrawBench and HRS benchmarks.

Yiyue Chen, Usman Akram, Chianing Wang et al.

Motivated by the high resource costs and privacy concerns associated with centralized machine learning, federated learning (FL) has emerged as an efficient alternative that enables clients to collaboratively train a global model while keeping their data local. However, in real-world deployments, client data distributions often evolve over time and differ significantly across clients, introducing heterogeneity that degrades the performance of standard FL algorithms. In this work, we introduce Fed-REACT, a federated learning framework designed for heterogeneous and evolving client data. Fed-REACT combines representation learning with evolutionary clustering in a two-stage process: (1) in the first stage, each client learns a local model to extracts feature representations from its data; (2) in the second stage, the server dynamically groups clients into clusters based on these representations and coordinates cluster-wise training of task-specific models for downstream objectives such as classification or regression. We provide a theoretical analysis of the representation learning stage, and empirically demonstrate that Fed-REACT achieves superior accuracy and robustness on real-world datasets.

Usman Akram, Haris Vikalo

Predicting the behavior of a dynamical system from noisy observations of its past outputs is a classical problem encountered across engineering and science. For linear systems with Gaussian inputs, the Kalman filter -- the best linear minimum mean-square error estimator of the state trajectory -- is optimal in the Bayesian sense. For nonlinear systems, Bayesian filtering is typically approached using suboptimal heuristics such as the Extended Kalman Filter (EKF), or numerical methods such as particle filtering (PF). In this work, we show that transformers, employed in an in-context learning (ICL) setting, can implicitly infer hidden states in order to predict the outputs of a wide family of dynamical systems, without test-time gradient updates or explicit knowledge of the system model. Specifically, when provided with a short context of past input-output pairs and, optionally, system parameters, a frozen transformer accurately predicts the current output. In linear-Gaussian regimes, its predictions closely match those of the Kalman filter; in nonlinear regimes, its performance approaches that of EKF and PF. Moreover, prediction accuracy degrades gracefully when key parameters, such as the state-transition matrix, are withheld from the context, demonstrating robustness and implicit parameter inference. These findings suggest that transformer in-context learning provides a flexible, non-parametric alternative for output prediction in dynamical systems, grounded in implicit latent-state estimation.

Hasan Burhan Beytur, Gustavo de Veciana, Haris Vikalo et al.

We study how to allocate resources for training and deployment of machine learning (ML) models under concept drift and limited budgets. We consider a setting in which a model provider distributes trained models to multiple clients whose devices support local inference but lack the ability to retrain those models, placing the burden of performance maintenance on the provider. We introduce a model-agnostic framework that captures the interaction between resource allocation, concept drift dynamics, and deployment timing. We show that optimal training policies depend critically on the aging properties of concept durations. Under sudden concept changes, we derive optimal training policies subject to budget constraints when concept durations follow distributions with Decreasing Mean Residual Life (DMRL), and show that intuitive heuristics are provably suboptimal under Increasing Mean Residual Life (IMRL). We further study model deployment under communication constraints, prove that the associated optimization problem is quasi-convex under mild conditions, and propose a randomized scheduling strategy that achieves near-optimal client-side performance. These results offer theoretical and algorithmic foundations for cost-efficient ML model management under concept drift, with implications for continual learning, distributed inference, and adaptive ML systems.

Usman Akram, Yiyue Chen, Haris Vikalo

Training automatic modulation classification (AMC) models on centrally aggregated data raises privacy concerns, incurs communication overhead, and often fails to confer robustness to channel shifts. Federated learning (FL) avoids central aggregation by training on distributed clients but remains sensitive to class imbalance, non-IID client distributions, and limited labeled samples. We propose FedSSL-AMC, which trains a causal, time-dilated CNN with triplet-loss self-supervision on unlabeled I/Q sequences across clients, followed by per-client SVMs on small labeled sets. We establish convergence of the federated representation learning procedure and a separability guarantee for the downstream classifier under feature noise. Experiments on synthetic and over-the-air datasets show consistent gains over supervised FL baselines under heterogeneous SNR, carrier-frequency offsets, and non-IID label partitions.

Seohyeon Cha, Huancheng Chen, Haris Vikalo

Federated continual learning (FCL) enables distributed client devices to learn from streaming data across diverse and evolving tasks. A major challenge to continual learning, catastrophic forgetting, is exacerbated in decentralized settings by the data heterogeneity, constrained communication and privacy concerns. We propose Federated gradient Projection-based Continual Learning with Task Identity Prediction (FedProTIP), a novel FCL framework that mitigates forgetting by projecting client updates onto the orthogonal complement of the subspace spanned by previously learned representations of the global model. This projection reduces interference with earlier tasks and preserves performance across the task sequence. To further address the challenge of task-agnostic inference, we incorporate a lightweight mechanism that leverages core bases from prior tasks to predict task identity and dynamically adjust the global model's outputs. Extensive experiments across standard FCL benchmarks demonstrate that FedProTIP significantly outperforms state-of-the-art methods in average accuracy, particularly in settings where task identities are a priori unknown.

Seohyeon Cha, Kevin Chan, Gustavo de Veciana et al.

The growing demand for intelligent services on resource-constrained edge devices has spurred the development of collaborative inference systems that distribute workloads across end devices, edge servers, and the cloud. While most existing frameworks focus on single-task, single-model scenarios, many real-world applications (e.g., autonomous driving and augmented reality) require concurrent execution of diverse tasks including detection, segmentation, and depth estimation. In this work, we propose a unified framework to jointly decide which multi-task models to deploy (onload) at clients and edge servers, and how to route queries across the hierarchy (offload) to maximize overall inference accuracy under memory, compute, and communication constraints. We formulate this as a mixed-integer program and introduce J3O (Joint Optimization of Onloading and Offloading), an alternating algorithm that (i) greedily selects models to onload via Lagrangian-relaxed submodular optimization and (ii) determines optimal offloading via constrained linear programming. We further extend J3O to account for batching at the edge, maintaining scalability under heterogeneous task loads. Experiments show J3O consistently achieves over $97\%$ of the optimal accuracy while incurring less than $15\%$ of the runtime required by the optimal solver across multi-task benchmarks.

Sangsu Lee, Xi Zheng, Jie Hua et al.

Pervasive computing applications commonly involve user's personal smartphones collecting data to influence application behavior. Applications are often backed by models that learn from the user's experiences to provide personalized and responsive behavior. While models are often pre-trained on massive datasets, federated learning has gained attention for its ability to train globally shared models on users' private data without requiring the users to share their data directly. However, federated learning requires devices to collaborate via a central server, under the assumption that all users desire to learn the same model. We define a new approach, opportunistic federated learning, in which individual devices belonging to different users seek to learn robust models that are personalized to their user's own experiences. However, instead of learning in isolation, these models opportunistically incorporate the learned experiences of other devices they encounter opportunistically. In this paper, we explore the feasibility and limits of such an approach, culminating in a framework that supports encounter-based pairwise collaborative learning. The use of our opportunistic encounter-based learning amplifies the performance of personalized learning while resisting overfitting to encountered data.

Abolfazl Hashemi, Anish Acharya, Rudrajit Das et al.

In decentralized optimization, it is common algorithmic practice to have nodes interleave (local) gradient descent iterations with gossip (i.e. averaging over the network) steps. Motivated by the training of large-scale machine learning models, it is also increasingly common to require that messages be {\em lossy compressed} versions of the local parameters. In this paper, we show that, in such compressed decentralized optimization settings, there are benefits to having {\em multiple} gossip steps between subsequent gradient iterations, even when the cost of doing so is appropriately accounted for e.g. by means of reducing the precision of compressed information. In particular, we show that having $O(\log\frac{1}ε)$ gradient iterations {with constant step size} - and $O(\log\frac{1}ε)$ gossip steps between every pair of these iterations - enables convergence to within $ε$ of the optimal value for smooth non-convex objectives satisfying Polyak-Łojasiewicz condition. This result also holds for smooth strongly convex objectives. To our knowledge, this is the first work that derives convergence results for nonconvex optimization under arbitrary communication compression.

Ziqi Ke, Haris Vikalo

Identification of the type of communication technology and/or modulation scheme based on detected radio signal are challenging problems encountered in a variety of applications including spectrum allocation and radio interference mitigation. They are rendered difficult due to a growing number of emitter types and varied effects of real-world channels upon the radio signal. Existing spectrum monitoring techniques are capable of acquiring massive amounts of radio and real-time spectrum data using compact sensors deployed in a variety of settings. However, state-of-the-art methods that use such data to classify emitter types and detect communication schemes struggle to achieve required levels of accuracy at a computational efficiency that would allow their implementation on low-cost computational platforms. In this paper, we present a learning framework based on an LSTM denoising auto-encoder designed to automatically extract stable and robust features from noisy radio signals, and infer modulation or technology type using the learned features. The algorithm utilizes a compact neural network architecture readily implemented on a low-cost computational platform while exceeding state-of-the-art accuracy. Results on realistic synthetic as well as over-the-air radio data demonstrate that the proposed framework reliably and efficiently classifies received radio signals, often demonstrating superior performance compared to state-of-the-art methods.

Monica Ribero, Haris Vikalo

Federated learning (FL) ameliorates privacy concerns in settings where a central server coordinates learning from data distributed across many clients. The clients train locally and communicate the models they learn to the server; aggregation of local models requires frequent communication of large amounts of information between the clients and the central server. We propose a novel, simple and efficient way of updating the central model in communication-constrained settings based on collecting models from clients with informative updates and estimating local updates that were not communicated. In particular, modeling the progression of model's weights by an Ornstein-Uhlenbeck process allows us to derive an optimal sampling strategy for selecting a subset of clients with significant weight updates. The central server collects updated local models from only the selected clients and combines them with estimated model updates of the clients that were not selected for communication. We test this policy on a synthetic dataset for logistic regression and two FL benchmarks, namely, a classification task on EMNIST and a realistic language modeling task using the Shakespeare dataset. The results demonstrate that the proposed framework provides significant reduction in communication while maintaining competitive or achieving superior performance compared to a baseline. Our method represents a new line of strategies for communication-efficient FL that is orthogonal to the existing user-local methods such as quantization or sparsification, thus complementing rather than aiming to replace those existing methods.

Mónica Ribero, Jette Henderson, Sinead Williamson et al.

Machine learning methods allow us to make recommendations to users in applications across fields including entertainment, dating, and commerce, by exploiting similarities in users' interaction patterns. However, in domains that demand protection of personally sensitive data, such as medicine or banking, how can we learn such a model without accessing the sensitive data, and without inadvertently leaking private information? We propose a new federated approach to learning global and local private models for recommendation without collecting raw data, user statistics, or information about personal preferences. Our method produces a set of prototypes that allows us to infer global behavioral patterns, while providing differential privacy guarantees for users in any database of the system. By requiring only two rounds of communication, we both reduce the communication costs and avoid the excessive privacy loss associated with iterative procedures. We test our framework on synthetic data as well as real federated medical data and Movielens ratings data. We show local adaptation of the global model allows our method to outperform centralized matrix-factorization-based recommender system models, both in terms of accuracy of matrix reconstruction and in terms of relevance of the recommendations, while maintaining provable privacy guarantees. We also show that our method is more robust and is characterized by smaller variance than individual models learned by independent entities.

Natalia M. Arzeno, Haris Vikalo

We are often interested in clustering objects that evolve over time and identifying solutions to the clustering problem for every time step. Evolutionary clustering provides insight into cluster evolution and temporal changes in cluster memberships while enabling performance superior to that achieved by independently clustering data collected at different time points. In this paper we introduce evolutionary affinity propagation (EAP), an evolutionary clustering algorithm that groups data points by exchanging messages on a factor graph. EAP promotes temporal smoothness of the solution to clustering time-evolving data by linking the nodes of the factor graph that are associated with adjacent data snapshots, and introduces consensus nodes to enable cluster tracking and identification of cluster births and deaths. Unlike existing evolutionary clustering methods that require additional processing to approximate the number of clusters or match them across time, EAP determines the number of clusters and tracks them automatically. A comparison with existing methods on simulated and experimental data demonstrates effectiveness of the proposed EAP algorithm.

Muhammad Usman, Wenxi Wang, Kaiyuan Wang et al.

This paper introduces the MCML approach for empirically studying the learnability of relational properties that can be expressed in the well-known software design language Alloy. A key novelty of MCML is quantification of the performance of and semantic differences among trained machine learning (ML) models, specifically decision trees, with respect to entire (bounded) input spaces, and not just for given training and test datasets (as is the common practice). MCML reduces the quantification problems to the classic complexity theory problem of model counting, and employs state-of-the-art model counters. The results show that relatively simple ML models can achieve surprisingly high performance (accuracy and F1-score) when evaluated in the common setting of using training and test datasets - even when the training dataset is much smaller than the test dataset - indicating the seeming simplicity of learning relational properties. However, MCML metrics based on model counting show that the performance can degrade substantially when tested against the entire (bounded) input space, indicating the high complexity of precisely learning these properties, and the usefulness of model counting in quantifying the true performance.

Abishek Sankararaman, Haris Vikalo, François Baccelli

Background: Haplotypes, the ordered lists of single nucleotide variations that distinguish chromosomal sequences from their homologous pairs, may reveal an individual's susceptibility to hereditary and complex diseases and affect how our bodies respond to therapeutic drugs. Reconstructing haplotypes of an individual from short sequencing reads is an NP-hard problem that becomes even more challenging in the case of polyploids. While increasing lengths of sequencing reads and insert sizes {\color{black} helps improve accuracy of reconstruction}, it also exacerbates computational complexity of the haplotype assembly task. This has motivated the pursuit of algorithmic frameworks capable of accurate yet efficient assembly of haplotypes from high-throughput sequencing data. Results: We propose a novel graphical representation of sequencing reads and pose the haplotype assembly problem as an instance of community detection on a spatial random graph. To this end, we construct a graph where each read is a node with an unknown community label associating the read with the haplotype it samples. Haplotype reconstruction can then be thought of as a two-step procedure: first, one recovers the community labels on the nodes (i.e., the reads), and then uses the estimated labels to assemble the haplotypes. Based on this observation, we propose ComHapDet - a novel assembly algorithm for diploid and ployploid haplotypes which allows both bialleleic and multi-allelic variants. Conclusions: Performance of the proposed algorithm is benchmarked on simulated as well as experimental data obtained by sequencing Chromosome $5$ of tetraploid biallelic \emph{Solanum-Tuberosum} (Potato). The results demonstrate the efficacy of the proposed method and that it compares favorably with the existing techniques.

Ziqi Ke, Haris Vikalo

Reconstructing components of a genomic mixture from data obtained by means of DNA sequencing is a challenging problem encountered in a variety of applications including single individual haplotyping and studies of viral communities. High-throughput DNA sequencing platforms oversample mixture components to provide massive amounts of reads whose relative positions can be determined by mapping the reads to a known reference genome; assembly of the components, however, requires discovery of the reads' origin -- an NP-hard problem that the existing methods struggle to solve with the required level of accuracy. In this paper, we present a learning framework based on a graph auto-encoder designed to exploit structural properties of sequencing data. The algorithm is a neural network which essentially trains to ignore sequencing errors and infers the posteriori probabilities of the origin of sequencing reads. Mixture components are then reconstructed by finding consensus of the reads determined to originate from the same genomic component. Results on realistic synthetic as well as experimental data demonstrate that the proposed framework reliably assembles haplotypes and reconstructs viral communities, often significantly outperforming state-of-the-art techniques.

Mahsa Ghasemi, Abolfazl Hashemi, Haris Vikalo et al.

We consider the problem of learning low-dimensional representations for large-scale Markov chains. We formulate the task of representation learning as that of mapping the state space of the model to a low-dimensional state space, called the kernel space. The kernel space contains a set of meta states which are desired to be representative of only a small subset of original states. To promote this structural property, we constrain the number of nonzero entries of the mappings between the state space and the kernel space. By imposing the desired characteristics of the representation, we cast the problem as a constrained nonnegative matrix factorization. To compute the solution, we propose an efficient block coordinate gradient descent and theoretically analyze its convergence properties.

Abolfazl Hashemi, Haris Vikalo, Gustavo de Veciana

Many problems in signal processing and machine learning can be formalized as weak submodular optimization tasks. For such problems, a simple greedy algorithm (\textsc{Greedy}) is guaranteed to find a solution achieving the objective with a value no worse than $1-e^{-1/c}$ of the optimal, where $c$ is the multiplicative weak-submodularity constant. Due to the high cost of querying large-scale systems, the complexity of \textsc{Greedy} becomes prohibitive in contemporary applications. In this work, we study the tradeoff between performance and complexity when one resorts to random sampling strategies to reduce the query complexity of \textsc{Greedy}. Specifically, we quantify the effect of uniform sampling strategies on \textsc{Greedy}'s performance through two metrics: (i) probability of identifying an optimal subset, and (ii) suboptimality with respect to the optimal solution. The latter implies that uniform sampling strategies with a fixed sampling size achieve a non-trivial approximation factor; however, we show that with overwhelming probability, these methods fail to find the optimal subset. Our analysis shows that the failure of uniform sampling strategies with fixed sample size can be circumvented by successively increasing the size of the search space. Building upon this insight, we propose a simple progressive stochastic greedy algorithm and study its approximation guarantees. Moreover, we demonstrate effectiveness of the proposed method in dimensionality reduction applications and feature selection tasks for clustering and object tracking.

Abolfazl Hashemi, Haris Vikalo

The problem of organizing data that evolves over time into clusters is encountered in a number of practical settings. We introduce evolutionary subspace clustering, a method whose objective is to cluster a collection of evolving data points that lie on a union of low-dimensional evolving subspaces. To learn the parsimonious representation of the data points at each time step, we propose a non-convex optimization framework that exploits the self-expressiveness property of the evolving data while taking into account representation from the preceding time step. To find an approximate solution to the aforementioned non-convex optimization problem, we develop a scheme based on alternating minimization that both learns the parsimonious representation as well as adaptively tunes and infers a smoothing parameter reflective of the rate of data evolution. The latter addresses a fundamental challenge in evolutionary clustering -- determining if and to what extent one should consider previous clustering solutions when analyzing an evolving data collection. Our experiments on both synthetic and real-world datasets demonstrate that the proposed framework outperforms state-of-the-art static subspace clustering algorithms and existing evolutionary clustering schemes in terms of both accuracy and running time, in a range of scenarios.

Somsubhra Barik, Haris Vikalo

Single individual haplotyping is an NP-hard problem that emerges when attempting to reconstruct an organism's inherited genetic variations using data typically generated by high-throughput DNA sequencing platforms. Genomes of diploid organisms, including humans, are organized into homologous pairs of chromosomes that differ from each other in a relatively small number of variant positions. Haplotypes are ordered sequences of the nucleotides in the variant positions of the chromosomes in a homologous pair; for diploids, haplotypes associated with a pair of chromosomes may be conveniently represented by means of complementary binary sequences. In this paper, we consider a binary matrix factorization formulation of the single individual haplotyping problem and efficiently solve it by means of alternating minimization. We analyze the convergence properties of the alternating minimization algorithm and establish theoretical bounds for the achievable haplotype reconstruction error. The proposed technique is shown to outperform existing methods when applied to synthetic as well as real-world Fosmid-based HapMap NA12878 datasets.

Abolfazl Hashemi, Rasoul Shafipour, Haris Vikalo et al.

We study the problem of sampling a bandlimited graph signal in the presence of noise, where the objective is to select a node subset of prescribed cardinality that minimizes the signal reconstruction mean squared error (MSE). To that end, we formulate the task at hand as the minimization of MSE subject to binary constraints, and approximate the resulting NP-hard problem via semidefinite programming (SDP) relaxation. Moreover, we provide an alternative formulation based on maximizing a monotone weak submodular function and propose a randomized-greedy algorithm to find a sub-optimal subset. We then derive a worst-case performance guarantee on the MSE returned by the randomized greedy algorithm for general non-stationary graph signals. The efficacy of the proposed methods is illustrated through numerical simulations on synthetic and real-world graphs. Notably, the randomized greedy algorithm yields an order-of-magnitude speedup over state-of-the-art greedy sampling schemes, while incurring only a marginal MSE performance loss.

Abolfazl Hashemi, Haris Vikalo

State-of-the-art algorithms for sparse subspace clustering perform spectral clustering on a similarity matrix typically obtained by representing each data point as a sparse combination of other points using either basis pursuit (BP) or orthogonal matching pursuit (OMP). BP-based methods are often prohibitive in practice while the performance of OMP-based schemes are unsatisfactory, especially in settings where data points are highly similar. In this paper, we propose a novel algorithm that exploits an accelerated variant of orthogonal least-squares to efficiently find the underlying subspaces. We show that under certain conditions the proposed algorithm returns a subspace-preserving solution. Simulation results illustrate that the proposed method compares favorably with BP-based method in terms of running time while being significantly more accurate than OMP-based schemes.

Abolfazl Hashemi, Haris Vikalo

We consider the Orthogonal Least-Squares (OLS) algorithm for the recovery of a $m$-dimensional $k$-sparse signal from a low number of noisy linear measurements. The Exact Recovery Condition (ERC) in bounded noisy scenario is established for OLS under certain condition on nonzero elements of the signal. The new result also improves the existing guarantees for Orthogonal Matching Pursuit (OMP) algorithm. In addition, This framework is employed to provide probabilistic guarantees for the case that the coefficient matrix is drawn at random according to Gaussian or Bernoulli distribution where we exploit some concentration properties. It is shown that under certain conditions, OLS recovers the true support in $k$ iterations with high probability. This in turn demonstrates that ${\cal O}\left(k\log m\right)$ measurements is sufficient for exact recovery of sparse signals via OLS.

Abolfazl Hashemi, Haris Vikalo

We study the problem of inferring a sparse vector from random linear combinations of its components. We propose the Accelerated Orthogonal Least-Squares (AOLS) algorithm that improves performance of the well-known Orthogonal Least-Squares (OLS) algorithm while requiring significantly lower computational costs. While OLS greedily selects columns of the coefficient matrix that correspond to non-zero components of the sparse vector, AOLS employs a novel computationally efficient procedure that speeds up the search by anticipating future selections via choosing $L$ columns in each step, where $L$ is an adjustable hyper-parameter. We analyze the performance of AOLS and establish lower bounds on the probability of exact recovery for both noiseless and noisy random linear measurements. In the noiseless scenario, it is shown that when the coefficients are samples from a Gaussian distribution, AOLS with high probability recovers a $k$-sparse $m$-dimensional sparse vector using ${\cal O}(k\log \frac{m}{k+L-1})$ measurements. Similar result is established for the bounded-noise scenario where an additional condition on the smallest nonzero element of the unknown vector is required. The asymptotic sampling complexity of AOLS is lower than the asymptotic sampling complexity of the existing sparse reconstruction algorithms. In simulations, AOLS is compared to state-of-the-art sparse recovery techniques and shown to provide better performance in terms of accuracy, running time, or both. Finally, we consider an application of AOLS to clustering high-dimensional data lying on the union of low-dimensional subspaces and demonstrate its superiority over existing methods.

Abolfazl Hashemi, Haris Vikalo

Sparse linear regression, which entails finding a sparse solution to an underdetermined system of linear equations, can formally be expressed as an $l_0$-constrained least-squares problem. The Orthogonal Least-Squares (OLS) algorithm sequentially selects the features (i.e., columns of the coefficient matrix) to greedily find an approximate sparse solution. In this paper, a generalization of Orthogonal Least-Squares which relies on a recursive relation between the components of the optimal solution to select L features at each step and solve the resulting overdetermined system of equations is proposed. Simulation results demonstrate that the generalized OLS algorithm is computationally efficient and achieves performance superior to that of existing greedy algorithms broadly used in the literature.

Natalia M. Arzeno, Karla A. Lawson, Sarah V. Duzinski et al.

Many in-hospital mortality risk prediction scores dichotomize predictive variables to simplify the score calculation. However, hard thresholding in these additive stepwise scores of the form "add x points if variable v is above/below threshold t" may lead to critical failures. In this paper, we seek to develop risk prediction scores that preserve clinical knowledge embedded in features and structure of the existing additive stepwise scores while addressing limitations caused by variable dichotomization. To this end, we propose a novel score structure that relies on a transformation of predictive variables by means of nonlinear logistic functions facilitating smooth differentiation between critical and normal values of the variables. We develop an optimization framework for inferring parameters of the logistic functions for a given patient population via cyclic block coordinate descent. The parameters may readily be updated as the patient population and standards of care evolve. We tested the proposed methodology on two populations: (1) brain trauma patients admitted to the intensive care unit of the Dell Children's Medical Center of Central Texas between 2007 and 2012, and (2) adult ICU patient data from the MIMIC II database. The results are compared with those obtained by the widely used PRISM III and SOFA scores. The prediction power of a score is evaluated using area under ROC curve, Youden's index, and precision-recall balance in a cross-validation study. The results demonstrate that the new framework enables significant performance improvements over PRISM III and SOFA in terms of all three criteria.