Rchr
J-GLOBAL ID:201801010438043202
Update date: Jun. 13, 2024
Bao Han
ツツミ フクム | Bao Han
Affiliation and department:
Job title:
Assistant Professor
Homepage URL (1):
https://hermite.jp/
Research field (1):
Statistical science
Research keywords (2):
machine learning
, 機械学習
Research theme for competitive and other funds (2):
- 2019 - 2022 限られた教師情報に基づく機械学習手法の開発
- 2018 - 2019 弱い教師データに基づく低分散なリスク推定方法の開発
Papers (31):
-
Guoxi Zhang, Han Bao 0002, Hisashi Kashima. Online Policy Learning from Offline Preferences. CoRR. 2024. abs/2403.10160
-
Shinsaku Sakaue, Han Bao 0002, Taira Tsuchiya, Taihei Oki. Online Structured Prediction with Fenchel-Young Losses and Improved Surrogate Regret for Online Multiclass Classification with Logistic Loss. CoRR. 2024. abs/2402.08180
-
Han Bao 0002, Ryuichiro Hataya, Ryo Karakida. Self-attention Networks Localize When QK-eigenspectrum Concentrates. CoRR. 2024. abs/2402.02098
-
Guillaume Houry, Han Bao 0002, Han Zhao 0002, Makoto Yamada. Fast 1-Wasserstein distance approximations using greedy strategies. AISTATS. 2024. 325-333
-
Ryoma Sato, Yuki Takezawa, Han Bao 0002, Kenta Niwa, Makoto Yamada. Embarrassingly Simple Text Watermarks. CoRR. 2023. abs/2310.08920
more...
MISC (2):
-
Yueh Hua Wu, Nontawat Charoenphakdee, Han Bao, Voot Tangkaratt, Masashi Sugiyama. Imitation learning from imperfect demonstration. 36th International Conference on Machine Learning, ICML 2019. 2019. 2019-June. 11826-11844
-
Han Bao, Gang Niu, Masashi Sugiyama. Classification from Pairwise Similarity and Unlabeled Data. 35th International Conference on Machine Learning, ICML 2018. 2018. 2. 763-781
Books (1):
-
Machine learning from weak supervision : an empirical risk minimization approach
The MIT Press 2022 ISBN:9780262047074
Professional career (1):
- Ph.D. in Information Science and Technology (The University of Tokyo)
Return to Previous Page