no code implementations • 11 Mar 2024 • Navdeep Kumar, Yashaswini Murthy, Itai Shufaro, Kfir Y. Levy, R. Srikant, Shie Mannor
We present the first finite time global convergence analysis of policy gradient in the context of infinite horizon average reward Markov decision processes (MDPs).
no code implementations • 5 Feb 2024 • Ron Dorfman, Naseem Yehya, Kfir Y. Levy
Byzantine-robust learning has emerged as a prominent fault-tolerant distributed machine learning framework.
no code implementations • 9 Apr 2023 • Kfir Y. Levy
We consider stochastic convex optimization problems where the objective is an expectation over smooth functions.
no code implementations • 9 Apr 2023 • Kfir Y. Levy
We consider distributed learning scenarios where M machines interact with a parameter server along several communication rounds in order to minimize a joint objective function.
no code implementations • 1 Feb 2023 • Ron Dorfman, Shay Vargaftik, Yaniv Ben-Itzhak, Kfir Y. Levy
Many compression techniques have been proposed to reduce the communication overhead of Federated Learning training procedures.
no code implementations • 31 May 2022 • Ilya Osadchiy, Kfir Y. Levy, Ron Meir
This solution comprises an inner learner that plays each episode separately, and an outer learner that updates the hyper-parameters of the inner algorithm between the episodes.
1 code implementation • 9 Feb 2022 • Ron Dorfman, Kfir Y. Levy
We consider stochastic optimization problems where data is drawn from a Markov chain.
no code implementations • 4 Feb 2022 • Tom Norman, Nir Weinberger, Kfir Y. Levy
In this work we go beyond these assumptions and investigate robust regression under a more general set of assumptions: $\textbf{(i)}$ we allow the covariance matrix to be either positive definite or positive semi definite, $\textbf{(ii)}$ we do not necessarily assume that the features are centered, $\textbf{(iii)}$ we make no further assumption beyond boundedness (sub-Gaussianity) of features and measurement noise.
no code implementations • 22 Nov 2021 • Jun-Kun Wang, Jacob Abernethy, Kfir Y. Levy
We develop an algorithmic framework for solving convex optimization problems using no-regret game dynamics.
no code implementations • 1 Nov 2021 • Kfir Y. Levy, Ali Kavis, Volkan Cevher
In this work we propose STORM+, a new method that is completely parameter-free, does not require large batch-sizes, and obtains the optimal $O(1/T^{1/3})$ rate for finding an approximate stationary point.
no code implementations • 23 Jun 2021 • Rotem Zamir Aviv, Ido Hakimi, Assaf Schuster, Kfir Y. Levy
We consider stochastic convex optimization problems, where several machines act asynchronously in parallel while sharing a common memory.
no code implementations • 23 Mar 2021 • Paulina Grnarova, Yannic Kilcher, Kfir Y. Levy, Aurelien Lucchi, Thomas Hofmann
Among known problems experienced by practitioners is the lack of convergence guarantees or convergence to a non-optimum cycle.
1 code implementation • NeurIPS 2021 • Menachem Adelman, Kfir Y. Levy, Ido Hakimi, Mark Silberstein
We propose a novel technique for faster deep neural network training which systematically applies sample-based approximation to the constituent tensor operations, i. e., matrix multiplications and convolutions.