Sanjay Krishnan

Joakim Nguyen, Jian Yu, Jinrui Fang et al.

Accurate diagnosis of pediatric brain tumors, starting with histopathology, presents unique challenges for deep learning, including severe data scarcity, class imbalance, and fine-grained morphologic overlap across diagnostically distinct subtypes. While pathology foundation models have advanced patch-level representation learning, their effective adaptation to weakly supervised pediatric brain tumor classification under limited data remains underexplored. In this work, we introduce an expert-guided contrastive fine-tuning framework for pediatric brain tumor diagnosis from whole-slide images (WSI). Our approach integrates contrastive learning into slide-level multiple instance learning (MIL) to explicitly regularize the geometry of slide-level representations during downstream fine-tuning. We propose both a general supervised contrastive setting and an expert-guided variant that incorporates clinically informed hard negatives targeting diagnostically confusable subtypes. Through comprehensive experiments on pediatric brain tumor WSI classification under realistic low-sample and class-imbalanced conditions, we demonstrate that contrastive fine-tuning yields measurable improvements in fine-grained diagnostic distinctions. Our experimental analyses reveal complementary strengths across different contrastive strategies, with expert-guided hard negatives promoting more compact intra-class representations and improved inter-class separation. This work highlights the importance of explicitly shaping slide-level representations for robust fine-grained classification in data-scarce pediatric pathology settings.

Edward C. Williams, Grace Su, Sandra R. Schloen et al.

Twenty-five hundred years ago, the paperwork of the Achaemenid Empire was recorded on clay tablets. In 1933, archaeologists from the University of Chicago's Oriental Institute (OI) found tens of thousands of these tablets and fragments during the excavation of Persepolis. Many of these tablets have been painstakingly photographed and annotated by expert cuneiformists, and now provide a rich dataset consisting of over 5,000 annotated tablet images and 100,000 cuneiform sign bounding boxes. We leverage this dataset to develop DeepScribe, a modular computer vision pipeline capable of localizing cuneiform signs and providing suggestions for the identity of each sign. We investigate the difficulty of learning subtasks relevant to cuneiform tablet transcription on ground-truth data, finding that a RetinaNet object detector can achieve a localization mAP of 0.78 and a ResNet classifier can achieve a top-5 sign classification accuracy of 0.89. The end-to-end pipeline achieves a top-5 classification accuracy of 0.80. As part of the classification module, DeepScribe groups cuneiform signs into morphological clusters. We consider how this automatic clustering approach differs from the organization of standard, printed sign lists and what we may learn from it. These components, trained individually, are sufficient to produce a system that can analyze photos of cuneiform tablets from the Achaemenid period and provide useful transliteration suggestions to researchers. We evaluate the model's end-to-end performance on locating and classifying signs, providing a roadmap to a linguistically-aware transliteration system, then consider the model's potential utility when applied to other periods of cuneiform writing.

Vatsal Patel, Sanjay Krishnan, Aimee Goncalves et al.

To simulate body organ motion due to breathing, heart beats, or peristaltic movements, we designed a low-cost, miniaturized SPRK (Stewart Platform Research Kit) to translate and rotate phantom tissue. This platform is 20cm x 20cm x 10cm to fit in the workspace of a da Vinci Research Kit (DVRK) surgical robot and costs $250, two orders of magnitude less than a commercial Stewart platform. The platform has a range of motion of +/- 1.27 cm in translation along x, y, and z directions and has motion modes for sinusoidal motion and breathing-inspired motion. Modular platform mounts were also designed for pattern cutting and debridement experiments. The platform's positional controller has a time-constant of 0.2 seconds and the root-mean-square error is 1.22 mm, 1.07 mm, and 0.20 mm in x, y, and z directions respectively. All the details, CAD models, and control software for the platform is available at github.com/BerkeleyAutomation/sprk.

Ted Shaowang, Sanjay Krishnan

The relevant features for a machine learning task may arrive as one or more continuous streams of data. Serving machine learning models over streams of data creates a number of interesting systems challenges in managing data routing, time-synchronization, and rate control. This paper presents EdgeServe, a distributed streaming system that can serve predictions from machine learning models in real time. We evaluate EdgeServe on three streaming prediction tasks: (1) human activity recognition, (2) autonomous driving, and (3) network intrusion detection.

Jian Yu, Joakim Nguyen, Jinrui Fang et al.

Accurate classification of pediatric central nervous system tumors remains challenging due to histological complexity and limited training data. While pathology foundation models have advanced whole-slide image (WSI) analysis, they often fail to leverage the rich, complementary information found in clinical text and tissue microarchitecture. To this end, we propose PathMoE, an interpretable multimodal framework that integrates H\&E slides, pathology reports, and nuclei-level cell graphs via an interaction-aware mixture-of-experts architecture built on state-of-the-art foundation models for each modality. By training specialized experts to capture modality uniqueness, redundancy, and synergy, PathMoE employs an input-dependent gating mechanism that dynamically weights these interactions, providing sample-level interpretability. We evaluate our framework on two dataset-specific classification tasks on an internal pediatric brain tumor dataset (PBT) and external TCGA datasets. PathMoE improves macro-F1 from 0.762 to 0.799 (+0.037) on PBT when integrating WSI, text, and graph modalities; on TCGA, augmenting WSI with graph knowledge improves macro-F1 from 0.668 to 0.709 (+0.041). These results demonstrate significant performance gains over state-of-the-art image-only baselines while revealing the specific modality interactions driving individual predictions. This interpretability is particularly critical for rare tumor subtypes, where transparent model reasoning is essential for clinical trust and diagnostic validation.

Shinan Liu, Ted Shaowang, Gerry Wan et al.

Network traffic analysis increasingly uses complex machine learning models as the internet consolidates and traffic gets more encrypted. However, over high-bandwidth networks, flows can easily arrive faster than model inference rates. The temporal nature of network flows limits simple scale-out approaches leveraged in other high-traffic machine learning applications. Accordingly, this paper presents ServeFlow, a solution for machine-learning model serving aimed at network traffic analysis tasks, which carefully selects the number of packets to collect and the models to apply for individual flows to achieve a balance between minimal latency, high service rate, and high accuracy. We identify that on the same task, inference time across models can differ by 1.8x - 141.3x, while the inter-packet waiting time is up to 6-8 orders of magnitude higher than the inference time! Based on these insights, we tailor a novel fast-slow model architecture for networking ML pipelines. Flows are assigned to a slower model only when the inferences from the fast model are deemed high uncertainty. ServeFlow is able to make inferences on 76.3% of flows in under 16ms, which is a speed-up of 40.5x on the median end-to-end serving latency while increasing the service rate and maintaining similar accuracy. Even with thousands of features per flow, it achieves a service rate of over 48.5k new flows per second on a 16-core CPU commodity server, which matches the order of magnitude of flow rates observed on city-level network backbones.

Ted Shaowang, Shinan Liu, Jonatas Marques et al.

Machine learning can analyze vast amounts of data generated by IoT devices to identify patterns, make predictions, and enable real-time decision-making. By processing sensor data, machine learning models can optimize processes, improve efficiency, and enhance personalized user experiences in smart systems. However, IoT systems are often deployed in sensitive environments such as households and offices, where they may inadvertently expose identifiable information, including location, habits, and personal identifiers. This raises significant privacy concerns, necessitating the application of data minimization -- a foundational principle in emerging data regulations, which mandates that service providers only collect data that is directly relevant and necessary for a specified purpose. Despite its importance, data minimization lacks a precise technical definition in the context of sensor data, where collections of weak signals make it challenging to apply a binary "relevant and necessary" rule. This paper provides a technical interpretation of data minimization in the context of sensor streams, explores practical methods for implementation, and addresses the challenges involved. Through our approach, we demonstrate that our framework can reduce user identifiability by up to 16.7% while maintaining accuracy loss below 1%, offering a viable path toward privacy-preserving IoT data processing.

Jinghan Zeng, Eugene Wu, Sanjay Krishnan

Many computer systems are now being redesigned to incorporate LLM-powered agents, enabling natural language input and more flexible operations. This paper focuses on handling database transactions created by large language models (LLMs). Transactions generated by LLMs may include semantic errors, requiring systems to treat them as long-lived. This allows for human review and, if the transaction is incorrect, removal from the database history. Any removal action must ensure the database's consistency (the "C" in ACID principles) is maintained throughout the process. We propose a novel middleware framework based on Invariant Satisfaction (I-Confluence), which ensures consistency by identifying and coordinating dependencies between long-lived transactions and new transactions. This middleware buffers suspicious or compensating transactions to manage coordination states. Using the TPC-C benchmark, we evaluate how transaction generation frequency, user reviews, and invariant completeness impact system performance. For system researchers, this study establishes an interactive paradigm between LLMs and database systems, providing an "undoing" mechanism for handling incorrect operations while guaranteeing database consistency. For system engineers, this paper offers a middleware design that integrates removable LLM-generated transactions into existing systems with minimal modifications.

Dale Decatur, Sanjay Krishnan

Visual graphics, such as plots, charts, and figures, are widely used to communicate statistical conclusions. Extracting information directly from such visualizations is a key sub-problem for effective search through scientific corpora, fact-checking, and data extraction. This paper presents a framework for automatically extracting compared variables from statistical charts. Due to the diversity and variation of charting styles, libraries, and tools, we leverage a computer vision based framework to automatically identify and localize visualization facets in line graphs, scatter plots, or bar graphs and can include multiple series per graph. The framework is trained on a large synthetically generated corpus of matplotlib charts and we evaluate the trained model on other chart datasets. In controlled experiments, our framework is able to classify, with 87.5% accuracy, the correlation between variables for graphs with 1-3 series per graph, varying colors, and solid line styles. When deployed on real-world graphs scraped from the internet, it achieves 72.8% accuracy (81.2% accuracy when excluding "hard" graphs). When deployed on the FigureQA dataset, it achieves 84.7% accuracy.

Adam Dziedzic, Vanlin Sathya, Muhammad Iqbal Rochman et al.

The application of Machine Learning (ML) techniques to complex engineering problems has proved to be an attractive and efficient solution. ML has been successfully applied to several practical tasks like image recognition, automating industrial operations, etc. The promise of ML techniques in solving non-linear problems influenced this work which aims to apply known ML techniques and develop new ones for wireless spectrum sharing between Wi-Fi and LTE in the unlicensed spectrum. In this work, we focus on the LTE-Unlicensed (LTE-U) specification developed by the LTE-U Forum, which uses the duty-cycle approach for fair coexistence. The specification suggests reducing the duty cycle at the LTE-U base-station (BS) when the number of co-channel Wi-Fi basic service sets (BSSs) increases from one to two or more. However, without decoding the Wi-Fi packets, detecting the number of Wi-Fi BSSs operating on the channel in real-time is a challenging problem. In this work, we demonstrate a novel ML-based approach which solves this problem by using energy values observed during the LTE-U OFF duration. It is relatively straightforward to observe only the energy values during the LTE-U BS OFF time compared to decoding the entire Wi-Fi packet, which would require a full Wi-Fi receiver at the LTE-U base-station. We implement and validate the proposed ML-based approach by real-time experiments and demonstrate that there exist distinct patterns between the energy distributions between one and many Wi-Fi AP transmissions. The proposed ML-based approach results in a higher accuracy (close to 99\% in all cases) as compared to the existing auto-correlation (AC) and energy detection (ED) approaches.

Adam Dziedzic, Sanjay Krishnan

Recent work has extensively shown that randomized perturbations of neural networks can improve robustness to adversarial attacks. The literature is, however, lacking a detailed compare-and-contrast of the latest proposals to understand what classes of perturbations work, when they work, and why they work. We contribute a detailed evaluation that elucidates these questions and benchmarks perturbation based defenses consistently. In particular, we show five main results: (1) all input perturbation defenses, whether random or deterministic, are equivalent in their efficacy, (2) attacks transfer between perturbation defenses so the attackers need not know the specific type of defense -- only that it involves perturbations, (3) a tuned sequence of noise layers across a network provides the best empirical robustness, (4) perturbation based defenses offer almost no robustness to adaptive attacks unless these perturbations are observed during training, and (5) adversarial examples in a close neighborhood of original inputs show an elevated sensitivity to perturbations in first and second-order analyses.

Rui Liu, Sanjay Krishnan, Aaron J. Elmore et al.

As neural networks are increasingly employed in machine learning practice, how to efficiently share limited training resources among a diverse set of model training tasks becomes a crucial issue. To achieve better utilization of the shared resources, we explore the idea of jointly training multiple neural network models on a single GPU in this paper. We realize this idea by proposing a primitive, called pack. We further present a comprehensive empirical study of pack and end-to-end experiments that suggest significant improvements for hyperparameter tuning. The results suggest: (1) packing two models can bring up to 40% performance improvement over unpacked setups for a single training step and the improvement increases when packing more models; (2) the benefit of the pack primitive largely depends on a number of factors including memory capacity, chip architecture, neural network structure, and batch size; (3) there exists a trade-off between packing and unpacking when training multiple neural network models on limited resources; (4) a pack-aware Hyperband is up to 2.7x faster than the original Hyperband, with this improvement growing as memory size increases and subsequently the density of models packed.

Vanlin Sathya, Adam Dziedzic, Monisha Ghosh et al.

According to the LTE-U Forum specification, a LTE-U base-station (BS) reduces its duty cycle from 50% to 33% when it senses an increase in the number of co-channel Wi-Fi basic service sets (BSSs) from one to two. The detection of the number of Wi-Fi BSSs that are operating on the channel in real-time, without decoding the Wi-Fi packets, still remains a challenge. In this paper, we present a novel machine learning (ML) approach that solves the problem by using energy values observed during LTE-U OFF duration. Observing the energy values (at LTE-U BS OFF time) is a much simpler operation than decoding the entire Wi-Fi packets. In this work, we implement and validate the proposed ML based approach in real-time experiments, and demonstrate that there are two distinct patterns between one and two Wi-Fi APs. This approach delivers an accuracy close to 100% compared to auto-correlation (AC) and energy detection (ED) approaches.

Adam Dziedzic, John Paparrizos, Sanjay Krishnan et al.

The convolutional layers are core building blocks of neural network architectures. In general, a convolutional filter applies to the entire frequency spectrum of the input data. We explore artificially constraining the frequency spectra of these filters and data, called band-limiting, during training. The frequency domain constraints apply to both the feed-forward and back-propagation steps. Experimentally, we observe that Convolutional Neural Networks (CNNs) are resilient to this compression scheme and results suggest that CNNs learn to leverage lower-frequency components. In particular, we found: (1) band-limited training can effectively control the resource usage (GPU and memory); (2) models trained with band-limited layers retain high prediction accuracy; and (3) requires no modification to existing training algorithms or neural network architectures to use unlike other compression schemes.

Zongheng Yang, Eric Liang, Amog Kamsetty et al.

Cardinality estimation has long been grounded in statistical tools for density estimation. To capture the rich multivariate distributions of relational tables, we propose the use of a new type of high-capacity statistical model: deep autoregressive models. However, direct application of these models leads to a limited estimator that is prohibitively expensive to evaluate for range or wildcard predicates. To produce a truly usable estimator, we develop a Monte Carlo integration scheme on top of autoregressive models that can efficiently handle range queries with dozens of dimensions or more. Like classical synopses, our estimator summarizes the data without supervision. Unlike previous solutions, we approximate the joint data distribution without any independence assumptions. Evaluated on real-world datasets and compared against real systems and dominant families of techniques, our estimator achieves single-digit multiplicative error at tail, an up to 90$\times$ accuracy improvement over the second best method, and is space- and runtime-efficient.

Ajay Kumar Tanwani, Jonathan Lee, Brijen Thananjeyan et al.

Generalizing manipulation skills to new situations requires extracting invariant patterns from demonstrations. For example, the robot needs to understand the demonstrations at a higher level while being invariant to the appearance of the objects, geometric aspects of objects such as its position, size, orientation and viewpoint of the observer in the demonstrations. In this paper, we propose an algorithm that learns a joint probability density function of the demonstrations with invariant formulations of hidden semi-Markov models to extract invariant segments (also termed as sub-goals or options), and smoothly follow the generated sequence of states with a linear quadratic tracking controller. The algorithm takes as input the demonstrations with respect to different coordinate systems describing virtual landmarks or objects of interest with a task-parameterized formulation, and adapt the segments according to the environmental changes in a systematic manner. We present variants of this algorithm in latent space with low-rank covariance decompositions, semi-tied covariances, and non-parametric online estimation of model parameters under small variance asymptotics; yielding considerably low sample and model complexity for acquiring new manipulation skills. The algorithm allows a Baxter robot to learn a pick-and-place task while avoiding a movable obstacle based on only 4 kinesthetic demonstrations.

Vatsal Patel, Sanjay Krishnan, Aimee Goncalves et al.

Anatomical structures are rarely static during a surgical procedure due to breathing, heartbeats, and peristaltic movements. Inspired by observing an expert surgeon, we propose an intermittent synchronization with the extrema of the rhythmic motion (i.e., the lowest velocity windows). We performed 2 experiments: (1) pattern cutting, and (2) debridement. In (1), we found that the intermittent synchronization approach, while 1.8x slower than tracking motion, was significantly more robust to noise and control latency, and it reduced the max cutting error by 2.6x In (2), a baseline approach with no synchronization achieves 62% success rate for each removal, while intermittent synchronization achieves 80%.

Richard Liaw, Sanjay Krishnan, Animesh Garg et al.

Rather than learning new control policies for each new task, it is possible, when tasks share some structure, to compose a "meta-policy" from previously learned policies. This paper reports results from experiments using Deep Reinforcement Learning on a continuous-state, discrete-action autonomous driving simulator. We explore how Deep Neural Networks can represent meta-policies that switch among a set of previously learned policies, specifically in settings where the dynamics of a new scenario are composed of a mixture of previously learned dynamics and where the state observation is possibly corrupted by sensing noise. We also report the results of experiments varying dynamics mixes, distractor policies, magnitudes/distributions of sensing noise, and obstacles. In a fully observed experiment, the meta-policy learning algorithm achieves 2.6x the reward achieved by the next best policy composition technique with 80% less exploration. In a partially observed experiment, the meta-policy learning algorithm converges after 50 iterations while a direct application of RL fails to converge even after 200 iterations.

Sanjay Krishnan, Roy Fox, Ion Stoica et al.

An option is a short-term skill consisting of a control policy for a specified region of the state space, and a termination condition recognizing leaving that region. In prior work, we proposed an algorithm called Deep Discovery of Options (DDO) to discover options to accelerate reinforcement learning in Atari games. This paper studies an extension to robot imitation learning, called Discovery of Deep Continuous Options (DDCO), where low-level continuous control skills parametrized by deep neural networks are learned from demonstrations. We extend DDO with: (1) a hybrid categorical-continuous distribution model to parametrize high-level policies that can invoke discrete options as well continuous control actions, and (2) a cross-validation method that relaxes DDO's requirement that users specify the number of options to be discovered. We evaluate DDCO in simulation of a 3-link robot in the vertical plane pushing a block with friction and gravity, and in two physical experiments on the da Vinci surgical robot, needle insertion where a needle is grasped and inserted into a silicone tissue phantom, and needle bin picking where needles and pins are grasped from a pile and categorized into bins. In the 3-link arm simulation, results suggest that DDCO can take 3x fewer demonstrations to achieve the same reward compared to a baseline imitation learning approach. In the needle insertion task, DDCO was successful 8/10 times compared to the next most accurate imitation learning baseline 6/10. In the surgical bin picking task, the learned policy successfully grasps a single object in 66 out of 99 attempted grasps, and in all but one case successfully recovered from failed grasps by retrying a second time.

Daniel Seita, Sanjay Krishnan, Roy Fox et al.

Automating precision subtasks such as debridement (removing dead or diseased tissue fragments) with Robotic Surgical Assistants (RSAs) such as the da Vinci Research Kit (dVRK) is challenging due to inherent non-linearities in cable-driven systems. We propose and evaluate a novel two-phase coarse-to-fine calibration method. In Phase I (coarse), we place a red calibration marker on the end effector and let it randomly move through a set of open-loop trajectories to obtain a large sample set of camera pixels and internal robot end-effector configurations. This coarse data is then used to train a Deep Neural Network (DNN) to learn the coarse transformation bias. In Phase II (fine), the bias from Phase I is applied to move the end-effector toward a small set of specific target points on a printed sheet. For each target, a human operator manually adjusts the end-effector position by direct contact (not through teleoperation) and the residual compensation bias is recorded. This fine data is then used to train a Random Forest (RF) to learn the fine transformation bias. Subsequent experiments suggest that without calibration, position errors average 4.55mm. Phase I can reduce average error to 2.14mm and the combination of Phase I and Phase II can reduces average error to 1.08mm. We apply these results to debridement of raisins and pumpkin seeds as fragment phantoms. Using an endoscopic stereo camera with standard edge detection, experiments with 120 trials achieved average success rates of 94.5%, exceeding prior results with much larger fragments (89.4%) and achieving a speedup of 2.1x, decreasing time per fragment from 15.8 seconds to 7.3 seconds. Source code, data, and videos are available at https://sites.google.com/view/calib-icra/.

Roy Fox, Sanjay Krishnan, Ion Stoica et al.

Augmenting an agent's control with useful higher-level behaviors called options can greatly reduce the sample complexity of reinforcement learning, but manually designing options is infeasible in high-dimensional and abstract state spaces. While recent work has proposed several techniques for automated option discovery, they do not scale to multi-level hierarchies and to expressive representations such as deep networks. We present Discovery of Deep Options (DDO), a policy-gradient algorithm that discovers parametrized options from a set of demonstration trajectories, and can be used recursively to discover additional levels of the hierarchy. The scalability of our approach to multi-level hierarchies stems from the decoupling of low-level option discovery from high-level meta-control policy learning, facilitated by under-parametrization of the high level. We demonstrate that using the discovered options to augment the action space of Deep Q-Network agents can accelerate learning by guiding exploration in tasks where random actions are unlikely to reach valuable states. We show that DDO is effective in adding options that accelerate learning in 4 out of 5 Atari RAM environments chosen in our experiments. We also show that DDO can discover structure in robot-assisted surgical videos and kinematics that match expert annotation with 72% accuracy.

Michael Laskey, Caleb Chuck, Jonathan Lee et al.

Motivated by recent advances in Deep Learning for robot control, this paper considers two learning algorithms in terms of how they acquire demonstrations. "Human-Centric" (HC) sampling is the standard supervised learning algorithm, where a human supervisor demonstrates the task by teleoperating the robot to provide trajectories consisting of state-control pairs. "Robot-Centric" (RC) sampling is an increasingly popular alternative used in algorithms such as DAgger, where a human supervisor observes the robot executing a learned policy and provides corrective control labels for each state visited. RC sampling can be challenging for human supervisors and prone to mislabeling. RC sampling can also induce error in policy performance because it repeatedly visits areas of the state space that are harder to learn. Although policies learned with RC sampling can be superior to HC sampling for standard learning models such as linear SVMs, policies learned with HC sampling may be comparable with highly-expressive learning models such as deep learning and hyper-parametric decision trees, which have little model error. We compare HC and RC using a grid world and a physical robot singulation task, where in the latter the input is a binary image of a connected set of objects on a planar worksurface and the policy generates a motion of the gripper to separate one object from the rest. We observe in simulation that for linear SVMs, policies learned with RC outperformed those learned with HC but that with deep models this advantage disappears. We also find that with RC, the corrective control labels provided by humans can be highly inconsistent. We prove there exists a class of examples where in the limit, HC is guaranteed to converge to an optimal policy while RC may fail to converge.

Sanjay Krishnan, Animesh Garg, Richard Liaw et al.

Reinforcement Learning (RL) struggles in problems with delayed rewards, and one approach is to segment the task into sub-tasks with incremental rewards. We propose a framework called Hierarchical Inverse Reinforcement Learning (HIRL), which is a model for learning sub-task structure from demonstrations. HIRL decomposes the task into sub-tasks based on transitions that are consistent across demonstrations. These transitions are defined as changes in local linearity w.r.t to a kernel function. Then, HIRL uses the inferred structure to learn reward functions local to the sub-tasks but also handle any global dependencies such as sequentiality. We have evaluated HIRL on several standard RL benchmarks: Parallel Parking with noisy dynamics, Two-Link Pendulum, 2D Noisy Motion Planning, and a Pinball environment. In the parallel parking task, we find that rewards constructed with HIRL converge to a policy with an 80% success rate in 32% fewer time-steps than those constructed with Maximum Entropy Inverse RL (MaxEnt IRL), and with partial state observation, the policies learned with IRL fail to achieve this accuracy while HIRL still converges. We further find that that the rewards learned with HIRL are robust to environment noise where they can tolerate 1 stdev. of random perturbation in the poses in the environment obstacles while maintaining roughly the same convergence rate. We find that HIRL rewards can converge up-to 6x faster than rewards constructed with IRL.

Sanjay Krishnan, Jiannan Wang, Eugene Wu et al.

Data cleaning is often an important step to ensure that predictive models, such as regression and classification, are not affected by systematic errors such as inconsistent, out-of-date, or outlier data. Identifying dirty data is often a manual and iterative process, and can be challenging on large datasets. However, many data cleaning workflows can introduce subtle biases into the training processes due to violation of independence assumptions. We propose ActiveClean, a progressive cleaning approach where the model is updated incrementally instead of re-training and can guarantee accuracy on partially cleaned data. ActiveClean supports a popular class of models called convex loss models (e.g., linear regression and SVMs). ActiveClean also leverages the structure of a user's model to prioritize cleaning those records likely to affect the results. We evaluate ActiveClean on five real-world datasets UCI Adult, UCI EEG, MNIST, Dollars For Docs, and WorldBank with both real and synthetic errors. Our results suggest that our proposed optimizations can improve model accuracy by up-to 2.5x for the same amount of data cleaned. Furthermore for a fixed cleaning budget and on all real dirty datasets, ActiveClean returns more accurate models than uniform sampling and Active Learning.

Martin Jaggi, Virginia Smith, Martin Takáč et al.

Communication remains the most significant bottleneck in the performance of distributed optimization algorithms for large-scale machine learning. In this paper, we propose a communication-efficient framework, CoCoA, that uses local computation in a primal-dual setting to dramatically reduce the amount of necessary communication. We provide a strong convergence rate analysis for this class of algorithms, as well as experiments on real-world distributed datasets with implementations in Spark. In our experiments, we find that as compared to state-of-the-art mini-batch versions of SGD and SDCA algorithms, CoCoA converges to the same .001-accurate solution quality on average 25x as quickly.