Publications
You can also find my articles on my Google Scholar profile.
* denotes equal contribution.
In Preparation
Mean Field Games for Randomized Impulse Control
Recommended citation: Haoyang Cao*, Zhouhao Yang*, "Mean Field Games for Randomized Impulse Control." In preparation (2026).
To Appear
Heavy-Tailed Flow Matching via Random Clocks
To appear in NeurIPS, 2026
Recommended citation: Zhouhao Yang*, Yezhen Wang*, Kenji Kawaguchi, Vladimir Braverman, Haoyang Cao, "Heavy-Tailed Flow Matching via Random Clocks." Accepted and to appear in NeurIPS 2026.
A Two-fold Randomization Framework for Impulse Control Problems
To appear in SIAM Journal on Control and Optimization, 2026
Recommended citation: 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.
Published
Training-Free versus Training-Based Intent Classification in LLMs: Accuracy, Robustness, and Failure Modes
Published in COLM, 2026
Recommended citation: Zhouhao Yang*, Nan Chen*, Soufiane Hayou, "Training-Free versus Training-Based Intent Classification in LLMs: Accuracy, Robustness, and Failure Modes." in Third Conference on Language Modeling, 2026.
Statistical Mean Estimation with Coded Relayed Observations
Published in IEEE Transactions on Information Theory, 2026
Recommended citation: Yan Hao Ling, Zhouhao Yang, Jonathan Scarlett, "Statistical Mean Estimation with Coded Relayed Observations." IEEE Transactions on Information Theory, vol. 72, no. 10, pp. 7329–7343, 2026. doi: 10.1109/TIT.2026.3716635.
Unlocking More Granular Control of Memory-Efficient LLM Finetuning
Published in IJCAI, 2026
Recommended citation: Yezhen Wang*, Zhouhao Yang*, Fanyi Pu, Kenji Kawaguchi, "Unlocking More Granular Control of Memory-Efficient LLM Finetuning." Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence (IJCAI-26), pp. 4985–4993, 2026. doi: 10.24963/ijcai.2026/555.
Bias-Variance Trade-off in Physics-Informed Neural Networks with Randomized Smoothing for High-Dimensional PDEs
Published in SIAM Journal on Scientific Computing, 2025
Recommended citation: 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.
Memory-Efficient Gradient Unrolling for Large-Scale Bi-level Optimization
Published in Neurips, 2024
Recommended citation: 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.
Distributionally Robust Policy Gradient for Offline Contextual Bandits
Published in AISTATS, 2023
Recommended citation: Zhouhao Yang, et al. "Distributionally robust policy gradient for offline contextual bandits." International Conference on Artificial Intelligence and Statistics. PMLR, 2023.
A General Framework for Accurate and Private Mean Estimation
Published in IEEE Signal Processing Letters, 2022
Recommended citation: Zhouhao Yang, Xingyu Xu, and Yuantao Gu. "A general framework for accurate and private mean estimation." IEEE Signal Processing Letters 29 (2022): 2293-2297.