336 citations · 1.1k across the 77 of their papers we have counts for
47 papers · 1 filter
Share Your Representation Only: Guaranteed Improvement of the Privacy-Utility Tradeoff in Federated Learning
Zebang Shen, Jiayuan Ye, Anmin Kang +2
Repeated parameter sharing in federated learning causes significant information leakage about private data, thus defeating its main purpose: data privacy. Mitigating the risk of th…
Min-Max Optimization under Delays
Arman Adibi, Aritra Mitra, Hamed Hassani
Delays and asynchrony are inevitable in large-scale machine-learning problems where communication plays a key role. As such, several works have extensively analyzed stochastic opti…
Text + Sketch: Image Compression at Ultra Low Rates
Eric Lei, Yiğit Berkay Uslu, Hamed Hassani +1
Recent advances in text-to-image generative models provide the ability to generate high-quality images from short text descriptions. These foundation models, when pre-trained on bi…
Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks
Liam Collins, Hamed Hassani, Mahdi Soltanolkotabi +2
An increasingly popular machine learning paradigm is to pretrain a neural network (NN) on many tasks offline, then adapt it to downstream tasks, often by re-training only the last…
Adversarial Training Should Be Cast as a Non-Zero-Sum Game
Alexander Robey, Fabian Latorre, George J. Pappas +2
One prominent approach toward resolving the adversarial vulnerability of deep neural networks is the two-player zero-sum paradigm of adversarial training, in which predictors are t…
Federated Neural Compression Under Heterogeneous Data
Eric Lei, Hamed Hassani, Shirin Saeedi Bidokhti
We discuss a federated learned compression problem, where the goal is to learn a compressor from real-world data which is scattered across clients and may be statistically heteroge…
Federated Temporal Difference Learning with Linear Function Approximation under Environmental Heterogeneity
Han Wang, Aritra Mitra, Hamed Hassani +2
We initiate the study of federated reinforcement learning under environmental heterogeneity by considering a policy evaluation problem. Our setup involves agents interacting wi…
Temporal Difference Learning with Compressed Updates: Error-Feedback meets Reinforcement Learning
Aritra Mitra, George J. Pappas, Hamed Hassani
In large-scale distributed machine learning, recent works have studied the effects of compressing gradients in stochastic optimization to alleviate the communication bottleneck. Th…
Fundamental Limits of Two-layer Autoencoders, and Achieving Them with Gradient Methods
Alexander Shevchenko, Kevin Kögler, Hamed Hassani +1
Autoencoders are a popular model in many branches of machine learning and lossy data compression. However, their fundamental limits, the performance of gradient methods and the fea…
Self-Consistency of the Fokker-Planck Equation
Zebang Shen, Zhenfu Wang, Satyen Kale +3
The Fokker-Planck equation (FPE) is the partial differential equation that governs the density evolution of the Itô process and is of great importance to the literature of statisti…
Collaborative Linear Bandits with Adversarial Agents: Near-Optimal Regret Bounds
Aritra Mitra, Arman Adibi, George J. Pappas +1
We consider a linear stochastic bandit problem involving agents that can collaborate via a central server to minimize regret. A fraction of these agents are adversarial and…
Straggler-Resilient Personalized Federated Learning
Isidoros Tziotis, Zebang Shen, Ramtin Pedarsani +2
Federated Learning is an emerging learning paradigm that allows training models from samples distributed across a large network of clients while respecting privacy and communicatio…
Toward Certified Robustness Against Real-World Distribution Shifts
Haoze Wu, Teruhiro Tagomori, Alexander Robey +6
We consider the problem of certifying the robustness of deep neural networks against real-world distribution shifts. To do so, we bridge the gap between hand-crafted specifications…
FedAvg with Fine Tuning: Local Updates Lead to Representation Learning
Liam Collins, Hamed Hassani, Aryan Mokhtari +1
The Federated Averaging (FedAvg) algorithm, which consists of alternating between a few local stochastic gradient updates at client nodes, followed by a model averaging update at t…
Distributed Statistical Min-Max Learning in the Presence of Byzantine Agents
Arman Adibi, Aritra Mitra, George J. Pappas +1
Recent years have witnessed a growing interest in the topic of min-max optimization, owing to its relevance in the context of generative adversarial networks (GANs), robust control…
Chordal Sparsity for Lipschitz Constant Estimation of Deep Neural Networks
Anton Xue, Lars Lindemann, Alexander Robey +3
Lipschitz constants of neural networks allow for guarantees of robustness in image classification, safety in controller design, and generalizability beyond the training data. As ca…
Binary Classification Under Attacks for General Noise Distribution
Payam Delgosha, Hamed Hassani, Ramtin Pedarsani
Adversarial examples have recently drawn considerable attention in the field of machine learning due to the fact that small perturbations in the data can result in major performanc…
Linear Stochastic Bandits over a Bit-Constrained Channel
Aritra Mitra, Hamed Hassani, George J. Pappas
One of the primary challenges in large-scale distributed learning stems from stringent communication constraints. While several recent works address this challenge for static optim…
What Functions Can Graph Neural Networks Generate?
Mohammad Fereydounian, Hamed Hassani, Amin Karbasi
In this paper, we fully answer the above question through a key algebraic condition on graph functions, called \textit{permutation compatibility}, that relates permutations of weig…
Probabilistically Robust Learning: Balancing Average- and Worst-case Performance
Alexander Robey, Luiz F. O. Chamon, George J. Pappas +1
Many of the successes of machine learning are based on minimizing an averaged loss function. However, it is well-known that this paradigm suffers from robustness issues that hinder…
Efficient and Robust Classification for Sparse Attacks
Mark Beliaev, Payam Delgosha, Hamed Hassani +1
In the past two decades we have seen the popularity of neural networks increase in conjunction with their classification accuracy. Parallel to this, we have also witnessed how frag…
The curse of overparametrization in adversarial training: Precise analysis of robust generalization for random features regression
Hamed Hassani, Adel Javanmard
Successful deep learning models often involve training neural network architectures that contain more parameters than the number of training samples. Such overparametrized models h…
Out-of-Distribution Robustness in Deep Learning Compression
Eric Lei, Hamed Hassani, Shirin Saeedi Bidokhti
In recent years, deep neural network (DNN) compression systems have proved to be highly effective for designing source codes for many natural sources. However, like many other mach…
Exploiting Heterogeneity in Robust Federated Best-Arm Identification
Aritra Mitra, Hamed Hassani, George Pappas
We study a federated variant of the best-arm identification problem in stochastic multi-armed bandits: a set of clients, each of whom can sample only a subset of the arms, collabor…