collaborators

5 papers

cs.LG2026

Local MixVR: Breaking the Communication-Sample Dependence in Distributed Learning

Tehila Dahan, Bassel Hamoud, Roie Reshef +2

Communication overhead is a crucial bottleneck in scalable distributed learning. While existing methods aim to efficiently utilize data points, such as Local SGD, Minibatch SGD, an…

cs.LG2026

Bringing Order to Asynchronous SGD: Towards Optimality under Data-Dependent Delays with Momentum

Tehila Dahan, Roie Reshef, Sharon Goldstein +1

Asynchronous stochastic gradient descent (SGD) enables scalable distributed training but suffers from gradient staleness. Existing mitigation strategies, such as delay-adaptive lea…

cs.LG2026

Optimal Sample Complexity for Single Time-Scale Actor-Critic with Momentum

Navdeep Kumar, Tehila Dahan, Lior Cohen +4

We establish an optimal sample complexity of for obtaining an -optimal global policy using a single-timescale actor-critic (AC) algorithm in infinite-horizon disco…

cs.LG2025

Weight for Robustness: A Comprehensive Approach towards Optimal Fault-Tolerant Asynchronous ML

Tehila Dahan, Kfir Y. Levy

We address the challenges of Byzantine-robust training in asynchronous distributed machine learning systems, aiming to enhance efficiency amid massive parallelization and heterogen…

cs.LG2025

-SGD: Stable Stochastic Optimization via a Double Momentum Mechanism

Tehila Dahan, Kfir Y. Levy

We consider stochastic convex optimization problems where the objective is an expectation over smooth functions. For this setting we suggest a novel gradient estimate that combines…