2 papers
stat.ML2026
Locally Private Online Quantile Regression: Estimation and Inference
Yi Liu, Qirui Hu
We study estimation and inference for online quantile regression under a one-report user-level $\eps$-locally differentially private ($\eps$-LDP) protocol. The main difficulty is t…
cs.LG2025
Intrinsic Benefits of Categorical Distributional Loss: Uncertainty-aware Regularized Exploration in Reinforcement Learning
Ke Sun, Yingnan Zhao, Enze Shi +4
The remarkable empirical performance of distributional reinforcement learning (RL) has garnered increasing attention to understanding its theoretical advantages over classical RL.…