@article{yu2026quantitative,title={Quantitative Analysis of the Effect of Density Ratio Estimation in Covariate Shift Adaptation},author={Yu, Chenglin and Zhou, Zhengyu and Liu, Weiwei},journal={Transactions on Machine Learning Research},year={2026},month=mar,url={https://openreview.net/forum?id=TtWsnXTYUV},}
AAAI
Rademacher Complexity for Distributionally Robust Learning
@inproceedings{zhou2026rademacher,title={Rademacher Complexity for Distributionally Robust Learning},author={Zhou, Zhengyu and Liu, Weiwei},booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},volume={40},number={34},pages={29098--29106},year={2026},doi={10.1609/aaai.v40i34.40147},url={https://ojs.aaai.org/index.php/AAAI/article/view/40147},}
@inproceedings{zhou2026robustness,title={On the Robustness of Bandit Multiple Testing},author={Zhou, Zhengyu and Liu, Weiwei},booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},volume={40},number={34},pages={29107--29114},year={2026},doi={10.1609/aaai.v40i34.40148},url={https://ojs.aaai.org/index.php/AAAI/article/view/40148},}
2025
ICML
An Error Analysis of Flow Matching for Deep Generative Modeling
@inproceedings{zhou2025error,title={An Error Analysis of Flow Matching for Deep Generative Modeling},author={Zhou, Zhengyu and Liu, Weiwei},booktitle={Proceedings of the 42nd International Conference on Machine Learning},series={Proceedings of Machine Learning Research},volume={267},pages={78903--78932},year={2025},publisher={PMLR},}
@inproceedings{zhou2024sequential,title={Sequential Kernel Goodness-of-fit Testing},author={Zhou, Zhengyu and Liu, Weiwei},booktitle={Proceedings of the 41st International Conference on Machine Learning},series={Proceedings of Machine Learning Research},volume={235},pages={62057--62075},year={2024},publisher={PMLR},}
AAAI
DRF: Improving Certified Robustness via Distributional Robustness Framework
@inproceedings{wang2024drf,title={DRF: Improving Certified Robustness via Distributional Robustness Framework},author={Wang, Zekai and Zhou, Zhengyu and Liu, Weiwei},booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},volume={38},number={14},pages={15752--15760},year={2024},doi={10.1609/aaai.v38i14.29504},url={https://ojs.aaai.org/index.php/AAAI/article/view/29504},}
AdaBoost is a well-known algorithm in boosting. Schapire and Singer propose an extension of AdaBoost, named AdaBoost.MH, for multi-class classification problems. Kégl shows empirically that AdaBoost.MH works better when the classical one-against-all base classifiers are replaced by factorized base classifiers containing a binary classifier and a vote (or code) vector. However, the factorization makes it much more difficult to provide a convergence result for the factorized version of AdaBoost.MH. Kégl then raises an open problem in COLT 2014 to look for a convergence result for the factorized AdaBoost.MH. In this work, we resolve this open problem by presenting a convergence result for AdaBoost.MH with factorized multi-class classifiers.
@article{JMLR:v24:22-0881,author={Zhou, Zhengyu and Liu, Weiwei},title={Sample Complexity for Distributionally Robust Learning under chi-square divergence},journal={Journal of Machine Learning Research},year={2023},volume={24},number={230},pages={1--27},}