Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Bohan Wang

Optimizing Information-theoretical Generalization Bounds via Anisotropic Noise in SGLD


Nov 03, 2021
Bohan Wang, Huishuai Zhang, Jieyu Zhang, Qi Meng, Wei Chen, Tie-Yan Liu

* Accepted by Neurips 2021 

  Access Paper or Ask Questions

Momentum Doesn't Change the Implicit Bias


Oct 08, 2021
Bohan Wang, Qi Meng, Huishuai Zhang, Ruoyu Sun, Wei Chen, Zhi-Ming Ma


  Access Paper or Ask Questions

Creating Training Sets via Weak Indirect Supervision


Oct 07, 2021
Jieyu Zhang, Bohan Wang, Xiangchen Song, Yujing Wang, Yaming Yang, Jing Bai, Alexander Ratner

* 40 pages 

  Access Paper or Ask Questions

Machine-Learning Non-Conservative Dynamics for New-Physics Detection


Jun 02, 2021
Ziming Liu, Bohan Wang, Qi Meng, Wei Chen, Max Tegmark, Tie-Yan Liu

* 17 pages, 7 figs, 2 tables; typo correction 

  Access Paper or Ask Questions

End-to-End Human Object Interaction Detection with HOI Transformer


Mar 08, 2021
Cheng Zou, Bohan Wang, Yue Hu, Junqi Liu, Qian Wu, Yu Zhao, Boxun Li, Chenguang Zhang, Chi Zhang, Yichen Wei, Jian Sun

* Accepted to CVPR2021 

  Access Paper or Ask Questions

Robustness, Privacy, and Generalization of Adversarial Training


Dec 25, 2020
Fengxiang He, Shaopeng Fu, Bohan Wang, Dacheng Tao


  Access Paper or Ask Questions

The Implicit Bias for Adaptive Optimization Algorithms on Homogeneous Neural Networks


Dec 11, 2020
Bohan Wang, Qi Meng, Wei Chen


  Access Paper or Ask Questions

Tighter Generalization Bounds for Iterative Differentially Private Learning Algorithms


Aug 07, 2020
Fengxiang He, Bohan Wang, Dacheng Tao


  Access Paper or Ask Questions

Piecewise linear activations substantially shape the loss surfaces of neural networks


Mar 27, 2020
Fengxiang He, Bohan Wang, Dacheng Tao

* Published as a conference paper at ICLR 2020 

  Access Paper or Ask Questions