Zihan Zhang

works on

calibration 1 online learning 1 randomized algorithms 1 regret bounds 1 sequential prediction 1

From the 1 of 3 linked papers with an AI index.

activity

20242026

collaborators

3 papers

cs.LG2026

Efficient Sequential Calibration with $O (T^{2/3 - I^µ})$ Error Bound

Zihan Zhang

The paper introduces an efficient randomized forecaster for online binary sequential calibration that achieves an expected calibration error of O(T^{2/3-ε}), improving upon the cla…

cs.LG2025

Settling the Sample Complexity of Online Reinforcement Learning

Zihan Zhang, Yuxin Chen, Jason D. Lee +1

A central issue lying at the heart of online reinforcement learning (RL) is data efficiency. While a number of recent works achieved asymptotically minimal regret in online RL, the…

stat.ML2024

Classification with Deep Neural Networks and Logistic Loss

Zihan Zhang, Lei Shi, Ding-Xuan Zhou

Deep neural networks (DNNs) trained with the logistic loss (i.e., the cross entropy loss) have made impressive advancements in various binary classification tasks. However, general…

Efficient Sequential Calibration with O(T2/3−I^µ) Error Bound

Settling the Sample Complexity of Online Reinforcement Learning

Classification with Deep Neural Networks and Logistic Loss

Efficient Sequential Calibration with $O (T^{2/3 - I^µ})$ Error Bound