Heyang Zhao

According to our database, Heyang Zhao authored at least 22 papers between 2021 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2026

Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability.

Qingyue Zhao, Kaixuan Ji, Heyang Zhao, Quanquan Gu

CoRR, May, 2026

On the Optimal Sample Complexity of Offline Multi-Armed Bandits with KL Regularization.

Kaixuan Ji, Qiwei Di, Heyang Zhao, Qingyue Zhao, Quanquan Gu

CoRR, May, 2026

Near-Optimal Regret for KL-Regularized Multi-Armed Bandits.

Kaixuan Ji, Qingyue Zhao, Heyang Zhao, Qiwei Di, Quanquan Gu

CoRR, March, 2026

2025

Best-of-Majority: Minimax-Optimal Strategy for Pass@<i>k</i> Inference Scaling.

Qiwei Di, Kaixuan Ji, Xuheng Li, Heyang Zhao, Quanquan Gu

CoRR, October, 2025

Nearly Optimal Sample Complexity of Offline KL-Regularized Contextual Bandits under Single-Policy Concentrability.

Qingyue Zhao, Kaixuan Ji, Heyang Zhao, Tong Zhang, Quanquan Gu

CoRR, February, 2025

Sharp Analysis for KL-Regularized Contextual Bandits and RLHF.

Heyang Zhao, Chenlu Ye, Quanquan Gu, Tong Zhang

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Logarithmic Regret for Online KL-Regularized Reinforcement Learning.

Heyang Zhao, Chenlu Ye, Wei Xiong, Quanquan Gu, Tong Zhang

Proceedings of the Forty-second International Conference on Machine Learning, 2025

Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double Exploration.

Heyang Zhao, Xingrui Yu, David Mark Bossens, Ivor W. Tsang, Quanquan Gu

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

A 0.16mm²450MHz-BW 72dB-SNDR Continuous-time Pipeline ADC with APF+HPF and APF+FIR Hybrid Delay Alignment Techniques.

Heyang Zhao, Yuxuan He, Yunsong Tao, Zhishuai Zhang, Yong Chen, Yi Zhong, Lu Jie, Nan Sun

Proceedings of the IEEE Custom Integrated Circuits Conference, 2025

CGCA-KAN: Correction-Guided Cluster-Aware Attention and KAN Enhanced Architecture for Medical Image Segmentation.

Peng Zhang, Yida Wu, Chen Liu, Heyang Zhao, Xingyu Liu, Zeyu Liu, Guanglei Zhang, Wenjian Wang

Proceedings of the IEEE International Conference on Bioinformatics and Biomedicine, 2025

2024

A Nearly Optimal and Low-Switching Algorithm for Reinforcement Learning with General Function Approximation.

Heyang Zhao, Jiafan He, Quanquan Gu

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Feel-Good Thompson Sampling for Contextual Dueling Bandits.

Xuheng Li, Heyang Zhao, Quanquan Gu

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning.

Qiwei Di, Heyang Zhao, Jiafan He, Quanquan Gu

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Variance-aware Regret Bounds for Stochastic Contextual Dueling Bandits.

Qiwei Di, Tao Jin, Yue Wu, Heyang Zhao, Farzad Farnoud, Quanquan Gu

Proceedings of the Twelfth International Conference on Learning Representations, 2024

S-lemma On Three Non-homogeneous Quadratic Functions And Its Applications In Signal Recovery.

Heyang Zhao, Mengxiao Zhang, Wenbao Ai

Proceedings of the 10th International Conference on Communication and Information Processing, 2024

2023

Optimal Online Generalized Linear Regression with Stochastic Noise and Its Application to Heteroscedastic Bandits.

Heyang Zhao, Dongruo Zhou, Jiafan He, Quanquan Gu

Proceedings of the International Conference on Machine Learning, 2023

Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processes.

Jiafan He, Heyang Zhao, Dongruo Zhou, Quanquan Gu

Proceedings of the International Conference on Machine Learning, 2023

Variance-Dependent Regret Bounds for Linear Bandits and Reinforcement Learning: Adaptivity and Computational Efficiency.

Heyang Zhao, Jiafan He, Dongruo Zhou, Tong Zhang, Quanquan Gu

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

2022

Bandit Learning with General Function Classes: Heteroscedastic Noise and Variance-dependent Regret Bounds.

Heyang Zhao, Dongruo Zhou, Jiafan He, Quanquan Gu

CoRR, 2022

VinciDecoder: Automatically Interpreting Provenance Graphs into Textual Forensic Reports with Application to OpenStack.

Azadeh Tabiban, Heyang Zhao, Yosr Jarraya, Makan Pourzandi, Lingyu Wang

Proceedings of the Secure IT Systems, 2022

ProvTalk: Towards Interpretable Multi-level Provenance Analysis in Networking Functions Virtualization (NFV).

Azadeh Tabiban, Heyang Zhao, Yosr Jarraya, Makan Pourzandi, Mengyuan Zhang, Lingyu Wang

Proceedings of the 29th Annual Network and Distributed System Security Symposium, 2022

2021

Linear Contextual Bandits with Adversarial Corruptions.

Heyang Zhao, Dongruo Zhou, Quanquan Gu

CoRR, 2021