A General Framework for Accurate and Private Mean Estimation
Zhouhao Yang, Xingyu Xu, and Yuantao Gu. "A general framework for accurate and private mean estimation." IEEE Signal Processing Letters 29 (2022): 2293-2297.
CV
Zhouhao Yang’s Curriculum Vitae
Education
- Bachelor of Mathematics and Applied Mathematics (Zhiyuan Honors Program) in Shanghai Jiao Tong University (2019.9-2023.6)
- Ph.D Student of Computer Science at National University of Singapore (2023.8-2024.7)
- Ph.D Candidate of Applied Mathematics and Statistics at the Johns Hopkins University (2024.8-present)
Publications
Distributionally Robust Policy Gradient for Offline Contextual Bandits
Zhouhao Yang, et al. "Distributionally robust policy gradient for offline contextual bandits." International Conference on Artificial Intelligence and Statistics. PMLR, 2023.
Memory-Efficient Gradient Unrolling for Large-Scale Bi-level Optimization
Qianli Shen, Yezhen Wang, Zhouhao Yang, Xiang Li, Haonan Wang, Yang Zhang, Jonathan Scarlett, Zhanxing Zhu, Kenji Kawaguchi, "Memory-Efficient Gradient Unrolling for Large-Scale Bi-level Optimization." The Thirty-Eighth Annual Conference on Neural Information Processing Systems, 2024.
Bias-Variance Trade-off in Physics-Informed Neural Networks with Randomized Smoothing for High-Dimensional PDEs
Zheyuan Hu*, Zhouhao Yang*, Yezhen Wang*, George Em Karniadakis, Kenji Kawaguchi, "Bias-Variance Trade-off in Physics-Informed Neural Networks with Randomized Smoothing for High-Dimensional PDEs." SIAM Journal on Scientific Computing 47.4 (2025): C846-C872.
Statistical Mean Estimation with Coded Relayed Observations
Yan Hao Ling, Zhouhao Yang, Jonathan Scarlett, "Statistical Mean Estimation with Coded Relayed Observations." To appear in IEEE Transactions on Information Theory, 2025.
A Two-fold Randomization Framework for Impulse Control Problems
Haoyang Cao*, Yuchao Dong*, Zhouhao Yang*, "A Two-fold Randomization Framework for Impulse Control Problems." To appear in SIAM Journal on Control and Optimization, 2026.
Training-Free versus Training-Based Intent Classification in LLMs: Accuracy, Robustness, and Failure Modes
Zhouhao Yang*, Nan Chen*, Soufiane Hayou, "Training-Free versus Training-Based Intent Classification in LLMs: Accuracy, Robustness, and Failure Modes." To appear in COLM 2026.
Unlocking More Granular Control of Memory-Efficient LLM Finetuning
Yezhen Wang*, Zhouhao Yang*, Fanyi Pu, Kenji Kawaguchi, "Unlocking More Granular Control of Memory-Efficient LLM Finetuning." To appear in IJCAI 2026.
Heavy-Tailed Flow Matching via Random Clocks
Zhouhao Yang, Yezhen Wang, Kenji Kawaguchi, Vladimir Braverman, Haoyang Cao, "Heavy-Tailed Flow Matching via Random Clocks." Under review at NeurIPS 2026.