3 papers
cs.LG2026
Adversary-Robust Learning from Fully Asynchronous Directional Derivative Estimates
Anik Kumar Paul, Nibedita Roy, Nagesh Talagani +3
We propose FAR-SIGN (Fully Asynchronous Robust optimization via SIGNed directional projections) for adversary-resilient learning in parameter-server--worker systems. FAR-SIGN achie…
stat.ML2026
Tight Convergence Rates for Online Distributed Linear Estimation with Adversarial Measurements
Nibedita Roy, Vishal Halder, Gugan Thoppe +4
We study mean estimation of a random vector in a distributed parameter-server-worker setup. Worker observes samples of , where is the th row of a…
cs.LG2024
Reinforcement Learning with Quasi-Hyperbolic Discounting
S. R. Eshwar, Mayank Motwani, Nibedita Roy +1
Reinforcement learning has traditionally been studied with exponential discounting or the average reward setup, mainly due to their mathematical tractability. However, such framewo…