Zhang, Haochen

12 publications

NeurIPS 2025 Breaking the Frozen Subspace: Importance Sampling for Low-Rank Optimization in LLM Pretraining Haochen Zhang, Junze Yin, Guanchu Wang, Zirui Liu, Lin Yang, Tianyi Zhang, Anshumali Shrivastava, Vladimir Braverman

ICLR 2025 Federated $q$-Learning with Reference-Advantage Decomposition: Almost Optimal Regret and Logarithmic Communication Cost Zhong Zheng, Haochen Zhang, Lingzhou Xue

ICML 2025 Gap-Dependent Bounds for Federated $q$-Learning Haochen Zhang, Zhong Zheng, Lingzhou Xue

ICLR 2025 Gap-Dependent Bounds for Q-Learning Using Reference-Advantage Decomposition Zhong Zheng, Haochen Zhang, Lingzhou Xue

NeurIPS 2025 Regret-Optimal Q-Learning with Low Cost for Single-Agent and Federated Reinforcement Learning Haochen Zhang, Zhong Zheng, Lingzhou Xue

AISTATS 2025 Statistical Guarantees for Lifelong Reinforcement Learning Using PAC-Bayes Theory Zhi Zhang, Chris Chow, Yasi Zhang, Yanchao Sun, Haochen Zhang, Eric Hanchen Jiang, Han Liu, Furong Huang, Yuchen Cui, Oscar Hernan Madrid Padilla

CVPRW 2024 Modeling Detailed Human Geometry with Adaptive Local Refinement Bang Du, Kunyao Chen, Haochen Zhang, Fei Yin, Baichuan Wu, Truong Nguyen

NeurIPS 2023 Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time Arvind Mahankali, Haochen Zhang, Kefan Dong, Margalit Glasgow, Tengyu Ma

ICCVW 2023 Robust AMD Stage Grading with Exclusively OCTA Modality Leveraging 3D Volume Haochen Zhang, Anna Heinke, Carlo Miguel B. Galang, Daniel N. Deussen, Bo Wen, Dirk-Uwe G. Bartsch, William R. Freeman, Truong Q. Nguyen, Cheolhong An

ICCV 2021 Unsupervised Real-World Super-Resolution: A Domain Adaptation Perspective Wei Wang, Haochen Zhang, Zehuan Yuan, Changhu Wang

NeurIPS 2019 On the Classification-Distortion-Perception Tradeoff Dong Liu, Haochen Zhang, Zhiwei Xiong

IJCAI 2017 From Decimation to Local Search and Back: A New Approach to MaxSAT Shaowei Cai, Chuan Luo, Haochen Zhang