publications
Under Review / Revision
- arXivImplicit Q-Learning and SARSA: Liberating Policy Control from Step-Size CalibrationUnder Review, 2026+
- arXivEfficient optimization of expensive black-box simulators via marginal means, with application to neutrino detector designUnder Revision, 2026+
- arXivStabilizing Temporal Difference Learning via Implicit Stochastic RecursionUnder Review, 2026+
Published & Accepted
2026
- AISTATSImplicit Updates for Average-Reward Temporal Difference LearningInternational Conference on Artificial Intelligence and Statistics, 2026
2025
2024
2023
2022
2019
- IWMSHigh-Dimensional Regression Under Correlated Design: An Extensive Simulation StudyInternational Workshop on Matrices and Statistics, 2019