5 papers
Minimax Quantile Lower Bounds for Interactive Statistical Decision Making with Privacy
Raghav Bongole, Amirreza Zamani, Tobias J. Oechtering +1
Minimax risk and regret are expectation-based criteria and do not capture rare but consequential failures. To address this concern, we develop a -explicit minimax-quantile theo…
Instantiating Bayesian CVaR lower bounds in Interactive Decision Making Problems
Raghav Bongole, Tobias J. Oechtering, Mikael Skoglund
Recent work established a generalized-Fano framework for lower bounding prior-predictive (Bayesian) CVaR in interactive statistical decision making. In this paper, we show how to i…
Generalizing the Fano inequality further
Raghav Bongole, Tobias J. Oechtering, Mikael Skoglund
Interactive statistical decision making (ISDM) features algorithm-dependent data generated through interaction. Existing information-theoretic lower bounds in ISDM largely target e…
Risk level dependent Minimax Quantile lower bounds for Interactive Statistical Decision Making
Raghav Bongole, Amirreza Zamani, Tobias J. Oechtering +1
Minimax risk and regret focus on expectation, missing rare failures critical in safety-critical bandits and reinforcement learning. Minimax quantiles capture these tails. Three str…
Information-Theoretic Minimax Regret Bounds for Reinforcement Learning based on Duality
Raghav Bongole, Amaury Gouverneur, Borja RodrÃguez-Gálvez +2
We study agents acting in an unknown environment where the agent's goal is to find a robust policy. We consider robust policies as policies that achieve high cumulative rewards for…