65 citations · 65 across the 9 of their papers we have counts for
Showing 2026Show all
3 papers · 1 filter
cs.LG2026
Differential Privacy of Gradient Descent on Perturbed Objectives
Austin Watkins, Raman Arora
Objective perturbation adds a random linear term to a regularized empirical risk and releases the exact perturbed minimizer. We study the finite computation obtained by releasing t…
cs.LG2026
Exact Unlearning in Reinforcement Learning
Thanh Nguyen-Tang, Raman Arora
We formulate the problem of \emph{exact unlearning} in reinforcement learning, where the goal is to design an efficient framework that enables the removal of any user's data upon d…
cs.LG2026
Minimax-Optimal Policy Regret in Partially Observable Markov Games
Raman Arora
We study sequential decision-making in partially observable environments against strategic, adaptive opponents, modeled as partially observable Markov games (POMGs). The central ch…