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 Huan Wang

Huan Wang

College of Informatics, Huazhong Agricultural University

Adapting Stepsizes by Momentumized Gradients Improves Optimization and Generalization


Jun 22, 2021
Yizhou Wang, Yue Kang, Can Qin, Yi Xu, Huan Wang, Yulun Zhang, Yun Fu

* 40 pages, 27 figures 

  Access Paper or Ask Questions

Understanding the Under-Coverage Bias in Uncertainty Estimation


Jun 10, 2021
Yu Bai, Song Mei, Huan Wang, Caiming Xiong


  Access Paper or Ask Questions

Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning


Jun 09, 2021
Tengyang Xie, Nan Jiang, Huan Wang, Caiming Xiong, Yu Bai


  Access Paper or Ask Questions

Evaluating State-of-the-Art Classification Models Against Bayes Optimality


Jun 07, 2021
Ryan Theisen, Huan Wang, Lav R. Varshney, Caiming Xiong, Richard Socher


  Access Paper or Ask Questions

Dynamical Isometry: The Missing Ingredient for Neural Network Pruning


May 12, 2021
Huan Wang, Can Qin, Yue Bai, Yun Fu

* 8 pages, 2 figures, 7 tables 

  Access Paper or Ask Questions

Emerging Paradigms of Neural Network Pruning


Mar 11, 2021
Huan Wang, Can Qin, Yulun Zhang, Yun Fu


  Access Paper or Ask Questions

Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games


Feb 23, 2021
Yu Bai, Chi Jin, Huan Wang, Caiming Xiong


  Access Paper or Ask Questions

Localized Calibration: Metrics and Recalibration


Feb 22, 2021
Rachel Luo, Aadyot Bhatnagar, Huan Wang, Caiming Xiong, Silvio Savarese, Yu Bai, Shengjia Zhao, Stefano Ermon


  Access Paper or Ask Questions

Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification


Feb 15, 2021
Yu Bai, Song Mei, Huan Wang, Caiming Xiong


  Access Paper or Ask Questions

Automatic Segmentation of Organs-at-Risk from Head-and-Neck CT using Separable Convolutional Neural Network with Hard-Region-Weighted Loss


Feb 03, 2021
Wenhui Lei, Haochen Mei, Zhengwentai Sun, Shan Ye, Ran Gu, Huan Wang, Rui Huang, Shichuan Zhang, Shaoting Zhang, Guotai Wang

* Accepted by Neurocomputing 

  Access Paper or Ask Questions

Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization


Dec 28, 2020
Stanislaw Jastrzebski, Devansh Arpit, Oliver Astrand, Giancarlo Kerg, Huan Wang, Caiming Xiong, Richard Socher, Kyunghyun Cho, Krzysztof Geras

* The last two authors contributed equally 

  Access Paper or Ask Questions

Neural Pruning via Growing Regularization


Dec 16, 2020
Huan Wang, Can Qin, Yulun Zhang, Yun Fu


  Access Paper or Ask Questions

An Event Correlation Filtering Method for Fake News Detection


Dec 13, 2020
Hao Li, Huan Wang, Guanghua Liu

* 24 pages, 5 figures, 3 tables 

  Access Paper or Ask Questions

Multi-head Knowledge Distillation for Model Compression


Dec 05, 2020
Huan Wang, Suhas Lohit, Michael Jones, Yun Fu

* Copyright: 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works 

  Access Paper or Ask Questions

Knowledge Distillation Thrives on Data Augmentation


Dec 05, 2020
Huan Wang, Suhas Lohit, Michael Jones, Yun Fu

* Code will be updated soon 

  Access Paper or Ask Questions

Unsupervised Paraphrase Generation via Dynamic Blocking


Oct 24, 2020
Tong Niu, Semih Yavuz, Yingbo Zhou, Huan Wang, Nitish Shirish Keskar, Caiming Xiong

* 10 pages 

  Access Paper or Ask Questions

How Important is the Train-Validation Split in Meta-Learning?


Oct 12, 2020
Yu Bai, Minshuo Chen, Pan Zhou, Tuo Zhao, Jason D. Lee, Sham Kakade, Huan Wang, Caiming Xiong


  Access Paper or Ask Questions

Towards Understanding Hierarchical Learning: Benefits of Neural Representations


Jun 24, 2020
Minshuo Chen, Yu Bai, Jason D. Lee, Tuo Zhao, Huan Wang, Caiming Xiong, Richard Socher


  Access Paper or Ask Questions

Collaborative Distillation for Ultra-Resolution Universal Style Transfer


Mar 24, 2020
Huan Wang, Yijun Li, Yuehai Wang, Haoji Hu, Ming-Hsuan Yang

* Accepted by CVPR 2020, higher-resolution images than the camera-ready version 

  Access Paper or Ask Questions

MNN: A Universal and Efficient Inference Engine


Feb 27, 2020
Xiaotang Jiang, Huan Wang, Yiliu Chen, Ziqi Wu, Lichuan Wang, Bin Zou, Yafeng Yang, Zongyang Cui, Yu Cai, Tianhang Yu, Chengfei Lv, Zhihua Wu

* Accepted by MLSys 2020 

  Access Paper or Ask Questions

Taylorized Training: Towards Better Approximation of Neural Network Training at Finite Width


Feb 24, 2020
Yu Bai, Ben Krause, Huan Wang, Caiming Xiong, Richard Socher


  Access Paper or Ask Questions

Neural Bayes: A Generic Parameterization Method for Unsupervised Representation Learning


Feb 20, 2020
Devansh Arpit, Huan Wang, Caiming Xiong, Richard Socher, Yoshua Bengio


  Access Paper or Ask Questions

Opposite Structure Learning for Semi-supervised Domain Adaptation


Feb 06, 2020
Can Qin, Lichen Wang, Qianqian Ma, Yu Yin, Huan Wang, Yun Fu

* 8 pages without citations 

  Access Paper or Ask Questions

Attentive Student Meets Multi-Task Teacher: Improved Knowledge Distillation for Pretrained Models


Nov 09, 2019
Linqing Liu, Huan Wang, Jimmy Lin, Richard Socher, Caiming Xiong


  Access Paper or Ask Questions

Global Capacity Measures for Deep ReLU Networks via Path Sampling


Oct 22, 2019
Ryan Theisen, Jason M. Klusowski, Huan Wang, Nitish Shirish Keskar, Caiming Xiong, Richard Socher


  Access Paper or Ask Questions

On the Generalization Gap in Reparameterizable Reinforcement Learning


May 29, 2019
Huan Wang, Stephan Zheng, Caiming Xiong, Richard Socher

* Proceedings of the 36 th International Conference on Machine Learning, Long Beach, California, PMLR 97, 2019 

  Access Paper or Ask Questions

Triplet Distillation for Deep Face Recognition


May 19, 2019
Yushu Feng, Huan Wang, Daniel T. Yi, Roland Hu

* 5 pages, 2 tables, accpeted by ICML 2019 ODML-CDNNR Workshop 

  Access Paper or Ask Questions

Structured Pruning for Efficient ConvNets via Incremental Regularization


Nov 20, 2018
Huan Wang, Qiming Zhang, Yuehai Wang, Haoji Hu

* Accepted by NIPS 2018 workshop on "Compact Deep Neural Network Representation with Industrial Applications" 

  Access Paper or Ask Questions