Arun Kumar

Arun Kumar, Aswathy Baiju, Radu Timofte et al.

Mobile deployment of facial age estimation requires models that balance predictive accuracy with low latency and compact size. In this work, we present MobileAgeNet, a lightweight age-regression framework that achieves an MAE of 4.65 years on the UTKFace held-out test set while maintaining efficient on-device inference with an average latency of 14.4 ms measured using the AI Benchmark application. The model is built on a pretrained MobileNetV3-Large backbone combined with a compact regression head, enabling real-time prediction on mobile devices. The training and evaluation pipeline is integrated into the NN LEMUR Dataset framework, supporting reproducible experimentation, structured hyperparameter optimization, and consistent evaluation. We employ bounded age regression together with a two-stage fine-tuning strategy to improve training stability and generalization. Experimental results show that MobileAgeNet achieves competitive accuracy with 3.23M parameters, and that the deployment pipeline from PyTorch training through ONNX export to TensorFlow Lite conversion - preserves predictive behavior without measurable degradation under practical on-device conditions. Overall, this work provides a practical, deployment-ready baseline for mobile-oriented facial age estimation.

Anusha Prakash, Arun Kumar, Ashish Seth et al.

Cross-lingual dubbing of lecture videos requires the transcription of the original audio, correction and removal of disfluencies, domain term discovery, text-to-text translation into the target language, chunking of text using target language rhythm, text-to-speech synthesis followed by isochronous lipsyncing to the original video. This task becomes challenging when the source and target languages belong to different language families, resulting in differences in generated audio duration. This is further compounded by the original speaker's rhythm, especially for extempore speech. This paper describes the challenges in regenerating English lecture videos in Indian languages semi-automatically. A prototype is developed for dubbing lectures into 9 Indian languages. A mean-opinion-score (MOS) is obtained for two languages, Hindi and Tamil, on two different courses. The output video is compared with the original video in terms of MOS (1-5) and lip synchronisation with scores of 4.09 and 3.74, respectively. The human effort also reduces by 75%.

Jean Pierre Sleiman, He Li, Alphonsus Adu-Bredu et al.

Achieving robust, human-like whole-body control on humanoid robots for agile, contact-rich behaviors remains a central challenge, demanding heavy per-skill engineering and a brittle process of tuning controllers. We introduce ZEST (Zero-shot Embodied Skill Transfer), a streamlined motion-imitation framework that trains policies via reinforcement learning from diverse sources -- high-fidelity motion capture, noisy monocular video, and non-physics-constrained animation -- and deploys them to hardware zero-shot. ZEST generalizes across behaviors and platforms while avoiding contact labels, reference or observation windows, state estimators, and extensive reward shaping. Its training pipeline combines adaptive sampling, which focuses training on difficult motion segments, and an automatic curriculum using a model-based assistive wrench, together enabling dynamic, long-horizon maneuvers. We further provide a procedure for selecting joint-level gains from approximate analytical armature values for closed-chain actuators, along with a refined model of actuators. Trained entirely in simulation with moderate domain randomization, ZEST demonstrates remarkable generality. On Boston Dynamics' Atlas humanoid, ZEST learns dynamic, multi-contact skills (e.g., army crawl, breakdancing) from motion capture. It transfers expressive dance and scene-interaction skills, such as box-climbing, directly from videos to Atlas and the Unitree G1. Furthermore, it extends across morphologies to the Spot quadruped, enabling acrobatics, such as a continuous backflip, through animation. Together, these results demonstrate robust zero-shot deployment across heterogeneous data sources and embodiments, establishing ZEST as a scalable interface between biological movements and their robotic counterparts.

Paridhi Singh, Gaurav Singh, Arun Kumar

Determining accurate bird's eye view (BEV) positions of objects and tracks in a scene is vital for various perception tasks including object interactions mapping, scenario extraction etc., however, the level of supervision required to accomplish that is extremely challenging to procure. We propose a light-weight, weakly supervised method to estimate 3D position of objects by jointly learning to regress the 2D object detections and scene's depth prediction in a single feed-forward pass of a network. Our proposed method extends a center-point based single-shot object detector, and introduces a novel object representation where each object is modeled as a BEV point spatio-temporally, without the need of any 3D or BEV annotations for training and LiDAR data at query time. The approach leverages readily available 2D object supervision along with LiDAR point clouds (used only during training) to jointly train a single network, that learns to predict 2D object detection alongside the whole scene's depth, to spatio-temporally model object tracks as points in BEV. The proposed method is computationally over $\sim$10x efficient compared to recent SOTA approaches while achieving comparable accuracies on KITTI tracking benchmark.

Kabir Nagrecha, Arun Kumar

In this paper, we propose Saturn, a new data system to improve the efficiency of multi-large-model training (e.g., during model selection/hyperparameter optimization). We first identify three key interconnected systems challenges for users building large models in this setting -- parallelism technique selection, distribution of GPUs over jobs, and scheduling. We then formalize these as a joint problem, and build a new system architecture to tackle these challenges simultaneously. Our evaluations show that our joint-optimization approach yields 39-49% lower model selection runtimes than typical current DL practice.

Autrio Das, Shreya Bollimuntha, Madala Venkata Renu Jeevesh et al.

What appears effortless to a human waiter remains a major challenge for robots. Manipulating objects nonprehensilely on a tray is inherently difficult, and the complexity is amplified in dual-arm settings. Such tasks are highly relevant to service robotics in domains such as hotels and hospitality, where robots must transport and reposition diverse objects with precision. We present DART, a novel dual-arm framework that integrates nonlinear Model Predictive Control (MPC) with an optimization-based impedance controller to achieve accurate object motion relative to a dynamically controlled tray. The framework systematically evaluates three complementary strategies for modeling tray-object dynamics as the state transition function within our MPC formulation: (i) a physics-based analytical model, (ii) an online regression based identification model that adapts in real-time, and (iii) a reinforcement learning-based dynamics model that generalizes across object properties. Our pipeline is validated in simulation with objects of varying mass, geometry, and friction coefficients. Extensive evaluations highlight the trade-offs among the three modeling strategies in terms of settling time, steady-state error, control effort, and generalization across objects. To the best of our knowledge, DART constitutes the first framework for non-prehensile dual-arm manipulation of objects on a tray. Project Link: https://dart-icra.github.io/dart/

Xiuwen Zheng, Arun Kumar, Amarnath Gupta

Modern data applications increasingly involve heterogeneous data managed in different models and stored across disparate database engines, often deployed as separate installs. Limited research has addressed cross-model query processing in federated environments. This paper takes a step toward bridging this gap by: (1) formally defining a class of cross-model join queries between a graph store and a relational store by proposing a unified algebra; (2) introducing one real-world benchmark and four semi-synthetic benchmarks to evaluate such queries; and (3) proposing a lightweight middleware, MICRO, for efficient query execution. At the core of MICRO is CMLero, a learning-to-rank-based query optimizer that selects efficient execution plans without requiring exact cost estimation. By avoiding the need to materialize or convert all data into a single model, which is often infeasible due to third-party data control or cost, MICRO enables native querying across heterogeneous systems. Experimental results on the benchmark workloads demonstrate that MICRO outperforms the state-of-the-art federated relational system XDB by up to 2.1x in total runtime across the full test set. On the 93 test queries of real-world benchmark, 14 queries achieve over 100 speedup, including 4 queries with more than 100x speedup; however, 4 queries experienced slowdowns of over 5 seconds, highlighting opportunities for future improvement of MICRO. Further comparisons show that CMLero consistently outperforms rule-based and regression-based optimizers, highlighting the advantage of learning-to-rank in complex cross-model optimization.

Arun Kumar, Paul Schrater

People aptly exhibit general intelligence behaviors through flexible problem-solving and the ability to adapt to novel situations by reusing and applying high-level knowledge acquired over time. In contrast, artificial agents tend to be specialists, lacking such generalist behaviors. To bridge this gap, artificial agents will require understanding and exploiting critical structured knowledge representations. We introduce a metacognitive reasoning framework, Knowledge-Interaction-eXecution (KIX), and argue that interactions with objects, by leveraging a type space, facilitate the learning of transferable interaction concepts and promote generalization. This framework offers a principled approach for integrating knowledge into reinforcement learning and holds promise as an enabler for generalist behaviors in artificial intelligence, robotics, and autonomous systems.

Arun Kumar, Paul Schrater

Invariant representations are core to representation learning, yet a central challenge remains: uncovering invariants that are stable and transferable without suppressing task-relevant signals. This raises fundamental questions, requiring further inquiry, about the appropriate level of abstraction at which such invariants should be defined and which aspects of a system they should characterize. Interpretation of the environment relies on abstract knowledge structures to make sense of the current state, which leads to interactions, essential drivers of learning and knowledge acquisition. Interpretation operates at the level of higher-order relational knowledge; hence, we propose that invariant structures must be where knowledge resides, specifically as partitions defined by the closure of relational paths within an abstract knowledge space. These partitions serve as the core invariant representations, forming the structural substrate where knowledge is stored and learning occurs. On the other hand, inter-partition connectors enable the deployment of these knowledge partitions encoding task-relevant transitions. Thus, invariant partitions provide the foundational primitives of structured representation. We formalize the computational foundations for structured relational representations of the invariant partitions based on closed semiring, a relational algebraic structure.

Mouad Abrini, Omri Abend, Dina Acklin et al. · cambridge

This volume includes a selection of papers presented at the Workshop on Advancing Artificial Intelligence through Theory of Mind held at AAAI 2025 in Philadelphia US on 3rd March 2025. The purpose of this volume is to provide an open access and curated anthology for the ToM and AI research community.

Paridhi Singh, Arun Kumar

This paper introduces an innovative approach to open world recognition (OWR), where we leverage knowledge acquired from known objects to address the recognition of previously unseen objects. The traditional method of object modeling relies on supervised learning with strict closed-set assumptions, presupposing that objects encountered during inference are already known at the training phase. However, this assumption proves inadequate for real-world scenarios due to the impracticality of accounting for the immense diversity of objects. Our hypothesis posits that object appearances can be represented as collections of "shareable" mid-level features, arranged in constellations to form object instances. By adopting this framework, we can efficiently dissect and represent both known and unknown objects in terms of their appearance cues. Our paper introduces a straightforward yet elegant method for modeling novel or unseen objects, utilizing established appearance cues and accounting for inherent uncertainties. This representation not only enables the detection of out-of-distribution objects or novel categories among unseen objects but also facilitates a deeper level of reasoning, empowering the identification of the superclass to which an unknown instance belongs. This novel approach holds promise for advancing open world recognition in diverse applications.

Kabir Nagrecha, Arun Kumar

Large language models such as GPT-3 & ChatGPT have transformed deep learning (DL), powering applications that have captured the public's imagination. These models are rapidly being adopted across domains for analytics on various modalities, often by finetuning pre-trained base models. Such models need multiple GPUs due to both their size and computational load, driving the development of a bevy of "model parallelism" techniques & tools. Navigating such parallelism choices, however, is a new burden for end users of DL such as data scientists, domain scientists, etc. who may lack the necessary systems knowhow. The need for model selection, which leads to many models to train due to hyper-parameter tuning or layer-wise finetuning, compounds the situation with two more burdens: resource apportioning and scheduling. In this work, we tackle these three burdens for DL users in a unified manner by formalizing them as a joint problem that we call SPASE: Select a Parallelism, Allocate resources, and SchedulE. We propose a new information system architecture to tackle the SPASE problem holistically, representing a key step toward enabling wider adoption of large DL models. We devise an extensible template for existing parallelism schemes and combine it with an automated empirical profiler for runtime estimation. We then formulate SPASE as an MILP. We find that direct use of an MILP-solver is significantly more effective than several baseline heuristics. We optimize the system runtime further with an introspective scheduling approach. We implement all these techniques into a new data system we call Saturn. Experiments with benchmark DL workloads show that Saturn achieves 39-49% lower model selection runtimes than typical current DL practice.

Kabir Nagrecha, Arun Kumar

Scaling up model depth and size is now a common approach to raise accuracy in many deep learning (DL) applications, as evidenced by the widespread success of multi-billion or even trillion parameter models in natural language processing (NLP) research. Despite success in DL research and at major technology companies, broader practical adoption of such large models among domain scientists and businesses is still bottlenecked by GPU memory limits, high training costs, and low GPU availability, even on public clouds. Model selection needs further compound these resource challenges: users often need to compare dozens of models with different hyper-parameters or neural architectures to suit their specific task and dataset. In this paper, we present Hydra, a system designed to tackle such challenges by enabling out-of-the-box scaling for multi-large-model DL workloads on even commodity GPUs in a resource-efficient manner. Hydra is the first approach to holistically optimize the execution of multi-model workloads for large DL models. We do this by adapting prior "model-parallel" execution schemes to work with scalable parameter offloading across the memory hierarchy and further hybridizing this approach with task-parallel job scheduling techniques. Hydra decouples scalability of model parameters from parallelism of execution, thus enabling DL users to train even a 6-billion parameter model on a single commodity GPU. It also fully exploits the speedup potential of task parallelism in multi-GPU setups, yielding near-linear strong scaling and making rigorous model selection perhaps more practical for such models. We evaluate end-to-end performance by fine-tuning GPT-2 for language modeling. We find that Hydra offers between 50% and 100% higher training throughput than even the best settings of state-of-the-art industrial frameworks such as DeepSpeed and GPipe for multi-large-model training.

Kiran Bisht, Arun Kumar

Fuzzy time series forecasting methods are very popular among researchers for predicting future values as they are not based on the strict assumptions of traditional time series forecasting methods. Non-stochastic methods of fuzzy time series forecasting are preferred by the researchers as they provide more significant forecasting results. There are generally, four factors that determine the performance of the forecasting method (1) number of intervals (NOIs) and length of intervals to partition universe of discourse (UOD) (2) fuzzification rules or feature representation of crisp time series (3) method of establishing fuzzy logic rule (FLRs) between input and target values (4) defuzzification rule to get crisp forecasted value. Considering the first two factors to improve the forecasting accuracy, we proposed a novel non-stochastic method fuzzy time series forecasting in which interval index number and membership value are used as input features to predict future value. We suggested a simple rounding-off range and suitable step size method to find the optimal number of intervals (NOIs) and used fuzzy c-means clustering process to divide UOD into intervals of unequal length. We implement support vector machine (SVM) to establish FLRs. To test our proposed method we conduct a simulated study on five widely used real time series and compare the performance with some recently developed models. We also examine the performance of the proposed model by using multi-layer perceptron (MLP) instead of SVM. Two performance measures RSME and SMAPE are used for performance analysis and observed better forecasting accuracy by the proposed model.

Arun Kumar, Mason Bell, Benjamin Mellinkoff et al.

Low-latency telerobotics can enable more intricate surface tasks on extraterrestrial planetary bodies than has ever been attempted. For humanity to create a sustainable lunar presence, well-developed collaboration between humans and robots is necessary to perform complex tasks. This paper presents a methodology to assess the human factors, situational awareness (SA) and cognitive load (CL), associated with teleoperated assembly tasks. Currently, telerobotic assembly on an extraterrestrial body has never been attempted, and a valid methodology to assess the associated human factors has not been developed. The Telerobotics Laboratory at the University of Colorado-Boulder created the Telerobotic Simulation System (TSS) which enables remote operation of a rover and a robotic arm. The TSS was used in a laboratory experiment designed as an analog to a lunar mission. The operator's task was to assemble a radio interferometer. Each participant completed this task under two conditions, remote teleoperation (limited SA) and local operation (optimal SA). The goal of the experiment was to establish a methodology to accurately measure the operator's SA and CL while performing teleoperated assembly tasks. A successful methodology would yield results showing greater SA and lower CL while operating locally. Performance metrics showed greater SA and lower CL in the local environment, supported by a 27% increase in the mean time to completion of the assembly task when operating remotely. Subjective measurements of SA and CL did not align with the performance metrics. Results from this experiment will guide future work attempting to accurately quantify the human factors associated with telerobotic assembly. Once an accurate methodology has been developed, we will be able to measure how new variables affect an operator's SA and CL to optimize the efficiency and effectiveness of telerobotic assembly tasks.

Ryan Cotterell, Arun Kumar, Hinrich Schütze

Morphological segmentation has traditionally been modeled with non-hierarchical models, which yield flat segmentations as output. In many cases, however, proper morphological analysis requires hierarchical structure -- especially in the case of derivational morphology. In this work, we introduce a discriminative, joint model of morphological segmentation along with the orthographic changes that occur during word formation. To the best of our knowledge, this is the first attempt to approach discriminative segmentation with a context-free model. Additionally, we release an annotated treebank of 7454 English words with constituency parses, encouraging future research in this area.

Jiayi Wang, Jiue-An Yang, Supun Nakandala et al.

This technical report records the experiments of applying multiple machine learning algorithms for predicting eating and food purchasing behaviors of free-living individuals. Data was collected with accelerometer, global positioning system (GPS), and body-worn cameras called SenseCam over a one week period in 81 individuals from a variety of ages and demographic backgrounds. These data were turned into minute-level features from sensors as well as engineered features that included time (e.g., time since last eating) and environmental context (e.g., distance to nearest grocery store). Algorithms include Logistic Regression, RBF-SVM, Random Forest, and Gradient Boosting. Our results show that the Gradient Boosting model has the highest mean accuracy score (0.7289) for predicting eating events before 0 to 4 minutes. For predicting food purchasing events, the RBF-SVM model (0.7395) outperforms others. For both prediction models, temporal and spatial features were important contributors to predicting eating and food purchasing events.

Alexander Ratner, Dan Alistarh, Gustavo Alonso et al.

Machine learning (ML) techniques are enjoying rapidly increasing adoption. However, designing and implementing the systems that support ML models in real-world deployments remains a significant obstacle, in large part due to the radically different development and deployment profile of modern ML methods, and the range of practical concerns that come with broader adoption. We propose to foster a new systems machine learning research community at the intersection of the traditional systems and ML communities, focused on topics such as hardware systems for ML, software systems for ML, and ML optimized for metrics beyond predictive accuracy. To do this, we describe a new conference, MLSys, that explicitly targets research at the intersection of systems and machine learning with a program committee split evenly between experts in systems and ML, and an explicit focus on topics at the intersection of the two.

Arun Kumar, Zhengwei Wu, Xaq Pitkow et al.

Animal behavior is not driven simply by its current observations, but is strongly influenced by internal states. Estimating the structure of these internal states is crucial for understanding the neural basis of behavior. In principle, internal states can be estimated by inverting behavior models, as in inverse model-based Reinforcement Learning. However, this requires careful parameterization and risks model-mismatch to the animal. Here we take a data-driven approach to infer latent states directly from observations of behavior, using a partially observable switching semi-Markov process. This process has two elements critical for capturing animal behavior: it captures non-exponential distribution of times between observations, and transitions between latent states depend on the animal's actions, features that require more complex non-markovian models to represent. To demonstrate the utility of our approach, we apply it to the observations of a simulated optimal agent performing a foraging task, and find that latent dynamics extracted by the model has correspondences with the belief dynamics of the agent. Finally, we apply our model to identify latent states in the behaviors of monkey performing a foraging task, and find clusters of latent states that identify periods of time consistent with expectant waiting. This data-driven behavioral model will be valuable for inferring latent cognitive states, and thereby for measuring neural representations of those states.

Aswin Kannan, Shanmukha C Guttula, Balaji Ganesan et al.

Hypernym discovery is the problem of finding terms that have is-a relationship with a given term. We introduce a new context type, and a relatedness measure to differentiate hypernyms from other types of semantic relationships. Our Document Structure measure is based on hierarchical position of terms in a document, and their presence or otherwise in definition text. This measure quantifies the document structure using multiple attributes, and classes of weighted distance functions.

Riddhiman Dasgupta, Balaji Ganesan, Aswin Kannan et al.

Entity Type Classification can be defined as the task of assigning category labels to entity mentions in documents. While neural networks have recently improved the classification of general entity mentions, pattern matching and other systems continue to be used for classifying personal data entities (e.g. classifying an organization as a media company or a government institution for GDPR, and HIPAA compliance). We propose a neural model to expand the class of personal data entities that can be classified at a fine grained level, using the output of existing pattern matching systems as additional contextual features. We introduce new resources, a personal data entities hierarchy with 134 types, and two datasets from the Wikipedia pages of elected representatives and Enron emails. We hope these resource will aid research in the area of personal data discovery, and to that effect, we provide baseline results on these datasets, and compare our method with state of the art models on OntoNotes dataset.

Arun Kumar, Karan Aggarwal, Paul Schrater

Users consume their favorite content in temporal proximity of consumption bundles according to their preferences and tastes. Thus, the underlying attributes of items implicitly match user preferences, however, current recommender systems largely ignore this fundamental driver in identifying matching items. In this work, we introduce a novel temporal proximity filtering method to enable items-matching. First, we demonstrate that proximity preferences exist. Second, we present an induced similarity metric in temporal proximity driven by user tastes and third, we show that this induced similarity can be used to learn items pairwise similarity in attribute space. The proposed model does not rely on any knowledge outside users' consumption bundles and provide a novel way to devise user preferences and tastes driven novel items recommender.

Amar Prakash Azad, Dinesh Garg, Priyanka Agrawal et al.

The goal behind Domain Adaptation (DA) is to leverage the labeled examples from a source domain so as to infer an accurate model in a target domain where labels are not available or in scarce at the best. A state-of-the-art approach for the DA is due to (Ganin et al. 2016), known as DANN, where they attempt to induce a common representation of source and target domains via adversarial training. This approach requires a large number of labeled examples from the source domain to be able to infer a good model for the target domain. However, in many situations obtaining labels in the source domain is expensive which results in deteriorated performance of DANN and limits its applicability in such scenarios. In this paper, we propose a novel approach to overcome this limitation. In our work, we first establish that DANN reduces the original DA problem into a semi-supervised learning problem over the space of common representation. Next, we propose a learning approach, namely TransDANN, that amalgamates adversarial learning and transductive learning to mitigate the detrimental impact of limited source labels and yields improved performance. Experimental results (both on text and images) show a significant boost in the performance of TransDANN over DANN under such scenarios. We also provide theoretical justification for the performance boost.

Arun Kumar, Navneet Paul, S N Omkar

Machine learning algorithms have found several applications in the field of robotics and control systems. The control systems community has started to show interest towards several machine learning algorithms from the sub-domains such as supervised learning, imitation learning and reinforcement learning to achieve autonomous control and intelligent decision making. Amongst many complex control problems, stable bipedal walking has been the most challenging problem. In this paper, we present an architecture to design and simulate a planar bipedal walking robot(BWR) using a realistic robotics simulator, Gazebo. The robot demonstrates successful walking behaviour by learning through several of its trial and errors, without any prior knowledge of itself or the world dynamics. The autonomous walking of the BWR is achieved using reinforcement learning algorithm called Deep Deterministic Policy Gradient(DDPG). DDPG is one of the algorithms for learning controls in continuous action spaces. After training the model in simulation, it was observed that, with a proper shaped reward function, the robot achieved faster walking or even rendered a running gait with an average speed of 0.83 m/s. The gait pattern of the bipedal walker was compared with the actual human walking pattern. The results show that the bipedal walking pattern had similar characteristics to that of a human walking pattern. The video presenting our experiment is available at https://goo.gl/NHXKqR.

Lingjiao Chen, Paraschos Koutris, Arun Kumar

Data analytics using machine learning (ML) has become ubiquitous in science, business intelligence, journalism and many other domains. While a lot of work focuses on reducing the training cost, inference runtime and storage cost of ML models, little work studies how to reduce the cost of data acquisition, which potentially leads to a loss of sellers' revenue and buyers' affordability and efficiency. In this paper, we propose a model-based pricing (MBP) framework, which instead of pricing the data, directly prices ML model instances. We first formally describe the desired properties of the MBP framework, with a focus on avoiding arbitrage. Next, we show a concrete realization of the MBP framework via a noise injection approach, which provably satisfies the desired formal properties. Based on the proposed framework, we then provide algorithmic solutions on how the seller can assign prices to models under different market scenarios (such as to maximize revenue). Finally, we conduct extensive experiments, which validate that the MBP framework can provide high revenue to the seller, high affordability to the buyer, and also operate on low runtime cost.

Divya Mahajan, Joon Kyung Kim, Jacob Sacks et al.

The data revolution is fueled by advances in machine learning, databases, and hardware design. Programmable accelerators are making their way into each of these areas independently. As such, there is a void of solutions that enables hardware acceleration at the intersection of these disjoint fields. This paper sets out to be the initial step towards a unifying solution for in-Database Acceleration of Advanced Analytics (DAnA). Deploying specialized hardware, such as FPGAs, for in-database analytics currently requires hand-designing the hardware and manually routing the data. Instead, DAnA automatically maps a high-level specification of advanced analytics queries to an FPGA accelerator. The accelerator implementation is generated for a User Defined Function (UDF), expressed as a part of an SQL query using a Python-embedded Domain-Specific Language (DSL). To realize an efficient in-database integration, DAnA accelerators contain a novel hardware structure, Striders, that directly interface with the buffer pool of the database. Striders extract, cleanse, and process the training data tuples that are consumed by a multi-threaded FPGA engine that executes the analytics algorithm. We integrate DAnA with PostgreSQL to generate hardware accelerators for a range of real-world and synthetic datasets running diverse ML algorithms. Results show that DAnA-enhanced PostgreSQL provides, on average, 8.3x end-to-end speedup for real datasets, with a maximum of 28.2x. Moreover, DAnA-enhanced PostgreSQL is, on average, 4.0x faster than the multi-threaded Apache MADLib running on Greenplum. DAnA provides these benefits while hiding the complexity of hardware design from data scientists and allowing them to express the algorithm in =30-60 lines of Python.

Harshit Kumar, Arvind Agarwal, Riddhiman Dasgupta et al.

Dialogue Act recognition associate dialogue acts (i.e., semantic labels) to utterances in a conversation. The problem of associating semantic labels to utterances can be treated as a sequence labeling problem. In this work, we build a hierarchical recurrent neural network using bidirectional LSTM as a base unit and the conditional random field (CRF) as the top layer to classify each utterance into its corresponding dialogue act. The hierarchical network learns representations at multiple levels, i.e., word level, utterance level, and conversation level. The conversation level representations are input to the CRF layer, which takes into account not only all previous utterances but also their dialogue acts, thus modeling the dependency among both, labels and utterances, an important consideration of natural dialogue. We validate our approach on two different benchmark data sets, Switchboard and Meeting Recorder Dialogue Act, and show performance improvement over the state-of-the-art methods by $2.2\%$ and $4.1\%$ absolute points, respectively. It is worth noting that the inter-annotator agreement on Switchboard data set is $84\%$, and our method is able to achieve the accuracy of about $79\%$ despite being trained on the noisy data.

Vraj Shah, Arun Kumar, Xiaojin Zhu

Machine learning (ML) over relational data is a booming area of the database industry and academia. While several projects aim to build scalable and fast ML systems, little work has addressed the pains of sourcing data and features for ML tasks. Real-world relational databases typically have many tables (often, dozens) and data scientists often struggle to even obtain and join all possible tables that provide features for ML. In this context, Kumar et al. showed recently that key-foreign key dependencies (KFKDs) between tables often lets us avoid such joins without significantly affecting prediction accuracy--an idea they called avoiding joins safely. While initially controversial, this idea has since been used by multiple companies to reduce the burden of data sourcing for ML. But their work applied only to linear classifiers. In this work, we verify if their results hold for three popular complex classifiers: decision trees, SVMs, and ANNs. We conduct an extensive experimental study using both real-world datasets and simulations to analyze the effects of avoiding KFK joins on such models. Our results show that these high-capacity classifiers are surprisingly and counter-intuitively more robust to avoiding KFK joins compared to linear classifiers, refuting an intuition from the prior work's analysis. We explain this behavior intuitively and identify open questions at the intersection of data management and ML theoretical research. All of our code and datasets are available for download from http://cseweb.ucsd.edu/~arunkk/hamlet.

Fengan Li, Lingjiao Chen, Yijing Zeng et al.

Data compression is a popular technique for improving the efficiency of data processing workloads such as SQL queries and more recently, machine learning (ML) with classical batch gradient methods. But the efficacy of such ideas for mini-batch stochastic gradient descent (MGD), arguably the workhorse algorithm of modern ML, is an open question. MGD's unique data access pattern renders prior art, including those designed for batch gradient methods, less effective. We fill this crucial research gap by proposing a new lossless compression scheme we call tuple-oriented compression (TOC) that is inspired by an unlikely source, the string/text compression scheme Lempel-Ziv-Welch, but tailored to MGD in a way that preserves tuple boundaries within mini-batches. We then present a suite of novel compressed matrix operation execution techniques tailored to the TOC compression scheme that operate directly over the compressed data representation and avoid decompression overheads. An extensive empirical evaluation with real-world datasets shows that TOC consistently achieves substantial compression ratios by up to 51x and reduces runtimes for MGD workloads by up to 10.2x in popular ML systems.

Arun Kumar, Paul Schrater

The vast majority of recommender systems model preferences as static or slowly changing due to observable user experience. However, spontaneous changes in user preferences are ubiquitous in many domains like media consumption and key factors that drive changes in preferences are not directly observable. These latent sources of preference change pose new challenges. When systems do not track and adapt to users' tastes, users lose confidence and trust, increasing the risk of user churn. We meet these challenges by developing a model of novelty preferences that learns and tracks latent user tastes. We combine three innovations: a new measure of item similarity based on patterns of consumption co-occurrence; model for {\em spontaneous} changes in preferences; and a learning agent that tracks each user's dynamic preferences and learns individualized policies for variety. The resulting framework adaptively provides users with novelty tailored to their preferences for change per se.

Xi Wu, Fengan Li, Arun Kumar et al.

While significant progress has been made separately on analytics systems for scalable stochastic gradient descent (SGD) and private SGD, none of the major scalable analytics frameworks have incorporated differentially private SGD. There are two inter-related issues for this disconnect between research and practice: (1) low model accuracy due to added noise to guarantee privacy, and (2) high development and runtime overhead of the private algorithms. This paper takes a first step to remedy this disconnect and proposes a private SGD algorithm to address \emph{both} issues in an integrated manner. In contrast to the white-box approach adopted by previous work, we revisit and use the classical technique of {\em output perturbation} to devise a novel "bolt-on" approach to private SGD. While our approach trivially addresses (2), it makes (1) even more challenging. We address this challenge by providing a novel analysis of the $L_2$-sensitivity of SGD, which allows, under the same privacy guarantees, better convergence of SGD when only a constant number of passes can be made over the data. We integrate our algorithm, as well as other state-of-the-art differentially private SGD, into Bismarck, a popular scalable SGD-based analytics system on top of an RDBMS. Extensive experiments show that our algorithm can be easily integrated, incurs virtually no overhead, scales well, and most importantly, yields substantially better (up to 4X) test accuracy than the state-of-the-art algorithms on many real datasets.