Five papers presented at NeurIPS 2022
The following five papers have been presented at the Thirty-sixth Conference on Neural Information Processing Systems (external pageNeurIPS 2022):
Fine-tuning Language Models over Slow Networks using Activation Compression with Guarantees. Jue Wang, Binhang Yuan, Luka Rimanic, Yongjun He, Tri Dao, Beidi Chen, Christopher Re, Ce Zhang (presented by Jue Wang and Binhang Yuan)
Decentralized Training of Foundation Models in Heterogeneous Environments. Binhang Yuan, Yongjun He, Tianyi Zhang, Jared Quincy Davis, Tri Dao, Beidi Chen, Percy Liang, Christopher Re, Ce Zhang (presented by Binhang Yuan and Yongjun He)
VF-PS: How to Select Important Participants in Vertical Federated Learning, Efficiently and Securely? Jiawei Jiang, Lukas Burkhalter, Fangcheng Fu, Bo Li, Bolin Ding, Bo Du, Anwar Hithnawi, Ce Zhang (presented by Jiawei Jiang)
Improving Certified Robustness via Statistical Learning with Logical Reasoning. Zhuolin Yang, Zhikuan Zhao, Boxin Wang, Jiawei Zhang, Linyi Li, Hengzhi Pei, Bojan Karlaš, Ji Liu, Heng Guo, Ce Zhang, Bo Li (presented by Zhuolin Yang and Zhikuan Zhao)
Certifying Some Distributional Fairness with Subpopulation Decomposition. Mintong Kang, Linyi Li, Maurice Weber, Yang Liu, Ce Zhang, Bo Li (presented by Mintong Kang and Linyi Li)