5 papers
Calibeating for general proper losses: A Bregman divergence approach
Maximilian Fichtl, Cristóbal Guzmán, Nishant A. Mehta
This work introduces a general framework for calibeating based on regret minimization. As compared to Foster and Hart's seminal calibeating work which had specialized treatments of…
Toward Simultaneously Optimal Regret in U-Calibration
Rafael Frongillo, Haipeng Luo, Nishant A. Mehta +1
U-calibration studies online forecasting algorithms whose predictions can be consumed by any unknown downstream agent, guaranteeing sublinear regret simultaneously for all proper l…
No-regret incentive-compatible online learning under exact truthfulness with non-myopic experts
Junpei Komiyama, Nishant A. Mehta, Ali Mortazavi
We study an online forecasting setting in which, over rounds, strategic experts each report a forecast to a mechanism, the mechanism selects one forecast, and then the outc…
Data-dependent Bounds with -Optimal Best-of-Both-Worlds Guarantees in Multi-Armed Bandits using Stability-Penalty Matching
Quan Nguyen, Shinji Ito, Junpei Komiyama +1
Existing data-dependent and best-of-both-worlds regret bounds for multi-armed bandits problems have limited adaptivity as they are either data-dependent but not best-of-both-worlds…
Beyond Minimax Rates in Group Distributionally Robust Optimization via a Novel Notion of Sparsity
Quan Nguyen, Nishant A. Mehta, Cristóbal Guzmán
The minimax sample complexity of group distributionally robust optimization (GDRO) has been determined up to a factor, where is the number of groups. In this work, we…