Huan's World

Merlion: A Machine Learning Library for Time Series, by Aadyot Bhatnagar, Paul Kassianik, Chenghao Liu, Tian Lan, Wenzhuo Yang, Rowan Cassius, Doyen Sahoo, Devansh Arpit, Sri Subramanian, Gerald Woo, Amrita Saha, Arun Kumar Jagota, Gokulakrishnan Gopalakrishnan, Manpreet Singh, K C Krithika, Sukumar Maddineni, Daeki Cho, Bo Zong, Yingbo Zhou, Caiming Xiong, Silvio Savarese, Steven Hoi and Huan Wang. Arxiv, 2021. [Github Repo], 1.9K stars in 3 weeks, ranked #1 by paperswithcode.com for 2 weeks.

Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning, by Tengyang Xie, Nan Jiang, Huan Wang, Caiming Xiong, Yu Bai. NeurIPS, 2021.

Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games, by Yu Bai, Chi Jin, Huan Wang, and Caiming Xiong. NeurIPS, 2021.

WarpDrive: Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning on a GPU, by Tian Lan, Sunil Srinivasa, Huan Wang, Stephan Zheng. Arxiv, 2021. [Github Repo]

On the Generalization Gap in Raparameterizable Reinforcement Learning, by Huan Wang, Stephan Zheng, Caiming Xiong, and Richard Socher. International Conference on Machine Learning (ICML), 2019.

Understanding the Under-Coverage Bias in Uncertainty Estimation, by Yu Bai, Song Mei, Huan Wang, Caiming Xiong. NeurIPS, 2021.

Localized Calibration: Metrics and Recalibration, by Rachel Luo, Aadyot Bhatnagar, Huan Wang, Caiming Xiong, Silvio Savarese, Yu Bai, Shengjia Zhao, Stefano Ermon. Arxiv, 2021.

Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification, by Yu Bai, Song Mei, Huan Wang, Caiming Xiong. ICML, 2021.

Unsupervised Paraphrasing with Pretrained Language Models, by Tong Niu, Semih Yavuz, Yingbo Zhou, Nitish Shirish Keskar, Huan Wang and Caiming Xiong. EMNLP, 2021.

BatchMixup: Improving Training by Interpolating Hidden States of the Entire Mini-batch, by Wenpeng Yin, Huan Wang, Jin Qu, Caiming Xiong. ACL.Findings, 2021.

Unsupervised Paraphrase Generation via Dynamic Blocking, by Tong Niu, Semih Yavuz, Yingbo Zhou, Huan Wang, Nitish Shirish Keskar, Caiming Xiong. Arxiv, 2021.

Attentive Student Meets Multi-Task Teacher: Improved Knowledge Distillation for Pretrained Models, by Linqing Liu, Huan Wang, Jimmy Lin, Richard Socher, Caiming Xiong. [arXiv:1911.03588], 2020.

Evaluating State-of-the-Art Classification Models Against Bayes Optimality, by Ryan Theisen, Huan Wang, Lav R Varshney, Caiming Xiong, and Richard Socher. NeurIPS, 2021.

Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization, by Stanislaw Jastrzebski, Devansh Arpit, Oliver Astrand, Giancarlo Kerg, Huan Wang, Caiming Xiong, Richard Socher, Kyunghyun Cho, Krzysztof Geras. ICML, 2021.

How Important is the Train-Validation Split in Meta-Learning?, by Yu Bai, Minshuo Chen, Pan Zhou, Tuo Zhao, Jason D Lee, Sham Kakade, Huan Wang, Caiming Xiong. ICML, 2021.

Towards understanding hierarchical learning: Benefits of neural representations, by Minshuo Chen, Yu Bai, Jason D Lee, Tuo Zhao, Huan Wang, Caiming Xiong, Richard Socher. NeurIPS, 2020.

Assessing Local Generalization Capability in Deep Models, by Huan Wang, Nitish Shirish Keskar, Caiming Xiong, Richard Socher. International Conference on Artificial Intelligence and Statistics (AISTATS), 2020.

Neural Bayes: A Generic Parameterization Method for Unsupervised Representation Learning, by Devansh Arpit, Huan Wang, Caiming Xiong, Richard Socher, Yoshua Bengio. [arXiv:2002.09046], 2020.

Taylorized Training: Towards Better Approximation of Neural Network Training at Finite Width, by Yu Bai, Ben Krause, Huan Wang, Caiming Xiong, Richard Socher. [arXiv:2002.04010], 2020.

Global Capacity Measures for Deep ReLU Networks via Path Sampling , by Ryan Theisen, Jason M. Klusowski, Huan Wang, Nitish Shirish Keskar, Caiming Xiong, Richard Socher. [arXiv:1910.10245], 2019.

DIME: An Information-Theoretic Difficulty Measure for AI Datasets , by Peiliang Zhang, Huan Wang, Nikhil Naik, Caiming Xiong, Richard Socher. [open review], 2019.

Identifying Generalization Properties in Neural Networks, by Huan Wang, Nitish Shirish Keskar, Caiming Xiong, and Richard Socher. [Integration of Deep Learning Theories, NeurIPS'18 Workshop] [arXiv:1809.07402] [blog post]

Adaptive Dropout with Rademacher Complexity Regularization, by Ke Zhai and Huan Wang. [equal contribution] International Conference on Learning Representations (ICLR), 2018.

Exact Recovery of Sparsely-Used Dictionaries, by Daniel Spielman, Huan Wang, and John Wright. [authors listed in alphabetical order] Best paper award of the 25th Conference on Learning Theory (COLT), Jun.2012. The arxiv version with details.

Semi-supervised Learning by Sparse Representation, by Shuicheng Yan and Huan Wang. SIAM International Conference on Data Mining (SDM), Apri. 2009.

A Convergent Solution to Tensor Subspace Learning, by Huan Wang, Shuicheng Yan, Thomas Huang and Xiaoou Tang. International Joint Conferences on Artificial Intelligence (IJCAI Oral Presentation), Jan. 2007.

Trace Ratio vs. Ratio Trace for Dimensionality Reduction, by Huan Wang, Shuicheng Yan, Dong Xu, Thomas Huang and Xiaoou Tang. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun.2007.

Mode-kn Factor Analysis for Image Ensembles, by Shuicheng Yan, Huan Wang, Jilin Tu, Xiaoou Tang, and Thomas Huang. IEEE Transaction on Image Processing (TIP), Mar.2009.

Synchronized Submanifold Embedding for Person-Independent Pose Estimation and Beyond, by Shuicheng Yan, Huan Wang, Yun Fu, Jun Yan, Xiaoou Tang, and Thomas S. Huang. IEEE Transactions on Image Processing (TIP), Vol.18, NO.1, Jan.2009.

Regression From Uncertain Labels and Its Applications to Soft Biometrics, by Shuicheng Yan, Huan Wang, Xiaoou Tang, Jianzhuang Liu, and Thomas Huang. IEEE Transactions on Information Forensics and Security (TIFS), Vol. 3, NO. 4, Dec.2008.

Learning Auto-Structured Regressor from Uncertain NonNegative Labels, by Shuicheng Yan, Huan Wang, Thomas Huang and Xiaoou Tang. IEEE International Conference on Computer Vision (ICCV), Oct.2007.

Transductive Regression Piloted by Inter-Manifold Relations, by Huan Wang, Shuicheng Yan, Thomas Huang, Jianzhuang Liu, and Xiaoou Tang. International Conference on Machine Learning (ICML), Jun. 2007.

Maximum unfolded embedding: Formulation, Solution, and Application for Image Clustering, by Huan Wang, Shuicheng Yan, Thomas Huang and Xiaoou Tang. ACM international conference on Multimedia (ACM MM), Oct.2006.

Ranking with Uncertain Labels , by Shuicheng Yan, Huan Wang, Thomas Huang and Xiaoou Tang. IEEE International Conference on Multimedia and Expo (ICME Oral Presentation), May.2007.

Ranking with Uncertain Labels and Its Application , by Shuicheng Yan, Huan Wang, Jianzhuang Liu, Xiaoou Tang, and Thomas Huang. Frontiers of Computer Science in China (Journal), 2007.

Correspondence Propagation with Weak Priors , by Huan Wang, Shuicheng Yan, Jianzhuang Liu, Thomas Huang, and Xiaoou Tang. IEEE Transaction on Image Processing (TIP), Jan.2009.

Misalignment-Robust Face Recognition , by Shuicheng Yan, Huan Wang, Jianzhuang Liu, Xiaoou Tang, and Thomas Huang. IEEE Transaction on Image Processing (TIP), Apri.2010.

Misalignment-Robust Face Recognition , by Huan Wang, Shuicheng Yan, Thomas Huang, Jianzhuang Liu, and Xiaoou Tang. IEEE International Conference on Computer Vision (CVPR), Jun.2008.

Exploring Feature Descriptors for Face Recognition , by Shuicheng Yan, Huan Wang, Xiaoou Tang, and Thomas Huang. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP Oral Presentation), Apri. 2007.

Exploring Intrinsic Structures from Samples: Supervised, Unsupervised, and Semisupervised Frameworks , by Huan Wang, Jun.2007.