Publications

I have published in the fields of machine learning (e.g., ICLR, NeurIPS, ICML, TPAMI, JMLR), computer vision (e.g., CVPR, ICCV, ECCV), signal processing (e.g., TIP, JSTSP), optimization and demography. 


(*asterisk indicates joint or alphabetical authorship) 

2024

HiRE: High Recall Approximate Top-k Estimation for Efficient LLM Inference

Yashas Samaga B L, Varun Yerram, Chong You, Srinadh Bhojanapalli, Sanjiv Kumar, Prateek Jain, Praneeth Netrapalli

It's an Alignment, Not a Trade-off: Revisiting Bias and Variance in Deep Models

Lin Chen, Michal Lukasik, Wittawat Jitkrittum, Chong You, Sanjiv Kumar

International Conference on Learning Representations (ICLR)

Functional Interpolation for Relative Positions Improves Long Context Transformers

Shanda Li, Chong You, Guru Guruganesh, Joshua Ainslie, Santiago Ontanon, Manzil Zaheer, Sumit Sanghai, Yiming Yang, Sanjiv Kumar, Srinadh Bhojanapalli

International Conference on Learning Representations (ICLR)

Deep Self-expressive Learning

Chen Zhao, Chun-guang Li, Wei He, Chong You

Conference on Parsimony and Learning (CPAL)

2023

Generalized Neural Collapse for a Large Number of Classes

Jiachen Jiang*, Jinxin Zhou*, Peng Wang, Qing Qu, Dustin Mixon, Chong You, Zhihui Zhu

The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers

Zonglin Li*, Chong You*, Srinadh Bhojanapalli, Daliang Li, Ankit Singh Rawat, Sashank J. Reddi, Ke Ye, Felix Chern, Felix Yu, Ruiqi Guo, Sanjiv Kumar

International Conference on Learning Representations (ICLR)

Teacher Guided Training: An Efficient Framework for Knowledge Transfer

Manzil Zaheer, Ankit Singh Rawat, Seungyeon Kim, Chong You, Himanshu Jain, Andreas Veit, Rob Fergus, Sanjiv Kumar

International Conference on Learning Representations (ICLR)

2022

Revisiting Sparse Convolutional Model for Visual Recognition

Xili Dai, Mingyang Li, Pengyuan Zhai, Shengbang Tong, Xingjian Gao, Shao-Lun Huang, Zhihui Zhu, Chong You, Yi Ma

Neural Information Processing Systems (NeurIPS) 

Are All Losses Created Equal: A Neural Collapse Perspective

Jinxin Zhou, Chong You, Xiao Li, Kangning Liu, Sheng Liu, Qing Qu, Zhihui Zhu

Neural Information Processing Systems (NeurIPS) 

Robust Training under Label Noise by Over-parameterization

Sheng Liu, Zhihui Zhu, Qing Qu,  Chong You

International Conference in Machine Learning (ICML) [talk1] [talk2] [code]

On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features

Jinxin Zhou*, Xiao Li*, Tianyu Ding, Chong You, Qing Qu*, Zhihui Zhu*

International Conference in Machine Learning (ICML) 

ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction 

Kwan Ho Ryan Chan*, Yaodong Yu*,  Chong You*, Haozhi Qi, John Wright, Yi Ma

Journal of Machine Learning Research (JMLR) [code]

Recovery and Generalization in Over-Realized Dictionary Learning

Jeremias Sulam, Chong You, Zhihui Zhu

Journal of Machine Learning Research (JMLR) 

2021

A Geometric Analysis of Neural Collapse with Unconstrained Features

Zhihui Zhu*, Tianyu Ding, Jinxin Zhou, Xiao Li, Chong You, Jeremias Sulam, Qing Qu

Neural Information Processing Systems (NeurIPS) (Spotlight presentation with acceptance rate 3%) [slides] [code] 

Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training

Sheng Liu*, Xiao Li*, Yuexiang Zhai, Chong You, Zhihui Zhu, Carlos Fernandez-Granda, Qing Qu

Neural Information Processing Systems (NeurIPS) [code]

A Nullspace Property for Subspace-Preserving Recovery

‪Mustafa Devrim Kaba, Chong You, Daniel P. Robinson, Enrique Mallada, and René Vidal

International Conference in Machine Learning (ICML) [talk]

Incremental Learning via Rate Reduction

Ziyang Wu*, Christina Baek*,  Chong You, Yi Ma

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), also atInternational Conference in Machine Learning (ICML) Workshop on Theory and Foundation of Continual Learning (Oral presentation)

Learning a Self-Expressive Network for Subspace Clustering 

Shangzhi Zhang, Chong You, René Vidal, Chun-Guang Li

IEEE Conference on Computer Vision and Pattern Recognition (CVPR)[slides] [poster] [code]

A Critique of Self-expressive Deep Subspace Clustering

Benjamin Haeffele, Chong You, René Vidal

International Conference on Learning Representations (ICLR)[poster]

2020

Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction

Yaodong Yu*, Kwan Ho Ryan Chan*, Chong You, Chaobing Song, Yi Ma

Neural Information Processing Systems (NeurIPS) [talk] [poster] [code]

Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization

Chong You*, Zhihui Zhu*, Qing Qu, Yi Ma

Neural Information Processing Systems (NeurIPS) (Spotlight presentation with acceptance rate 4%) [talk] [slides] [poster] [code] 

Deep Networks from the Principle of Rate Reduction

Kwan Ho Ryan Chan*, Yaodong Yu*,  Chong You*, Haozhi Qi, John Wright, Yi Ma

Neural Information Processing Systems (NeurIPS) Beyond Backprop Workshop [code]

Deep Isometric Learning for Visual Recognition

Haozhi Qi, Chong You, Xiaolong Wang, Yi Ma, Jitendra Malik

International Conference in Machine Learning (ICML) [talk] [slides] [code] [project page] 

Rethinking Bias-Variance Trade-off for Generalization of Neural Networks

Zitong Yang*, Yaodong Yu*, Chong You, Jacob Steinhardt, Yi Ma

International Conference in Machine Learning (ICML) [talk] [slides] [code]

Stochastic Sparse Subspace Clustering

Ying Chen, Chun-Guang Li, Chong You

IEEE Conference on Computer Vision and Pattern Recognition (CVPR) [talk] [code]

Self-Representation Based Unsupervised Exemplar Selection in a Union of Subspaces

Chong You,  Chi Li, Daniel P. Robinson, René Vidal

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Conference version at ECCV '18

Basis Pursuit and Orthogonal Matching Pursuit for Subspace-preserving Recovery: Theoretical Analysis

Daniel P. Robinson*, René Vidal*, Chong You*

2019

Is an Affine Constraint Needed for Affine Subspace Clustering?

Chong You, Chun-Guang Li, Daniel P. Robinson, René Vidal

International Conference on Computer Vision (ICCV)  [slides] [poster] 

Classifying and Comparing Approaches to Subspace Clustering with Missing Data

Connor Lane, Ron Boger, Chong You, Manolis Tsakiris, Benjamin Haeffele, René Vidal

International Workshop on Robust Subspace Learning and Applications in Computer Vision, in conjunction with International Conference on Computer Vision (ICCV)

Self-Supervised Convolutional Subspace Clustering Network

Junjian Zhang, Chun-Guang Li, Chong You, Xianbiao Qi, Honggang Zhang, Jun Guo, Zhouchen Lin

IEEE Conference on Computer Vision and Pattern Recognition (CVPR)[code]

Improving Age Measurement in Low- and Middle-income Countries Through Computer Vision: A Test in Senegal

Stephane Helleringer, Chong You, Laurence Fleury, Laetitia Douillot, Cheikh Tidiane Ndiaye, Valerie Delaunay, René Vidal

Demographic Research

2018

On Geometric Analysis of Affine Sparse Subspace Clustering

Chun-Guang Li*, Chong You*,  René Vidal,

IEEE Journal of Selected Topics in Signal Processing (JSTSP)

A Scalable Exemplar-based Subspace Clustering Algorithm for Class-Imbalanced Data

Chong You, Chi Li, Daniel P. Robinson, René Vidal

European Conference in Computer Vision (ECCV), Journal version at TPAMI '20[poster] [code]

A Nonconvex Formulation for Low Rank Subspace Clustering: Algorithms and Convergence Analysis

Hao Jiang*, Daniel P. Robinson*, René Vidal*, Chong You*

Computational Optimization and Applications

2017

Provable Self-Representation Based Outlier Detection in a Union of Subspaces

Chong You, Daniel P. Robinson, René Vidal

IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (Spotlight oral presentation with acceptance rate 8%) [talk] [slides] [poster] [code] 

Structured Sparse Subspace Clustering: A Joint Affinity Learning and Subspace Clustering Framework

Chun-Guang Li, Chong You, René Vidal 

IEEE Transactions on Image Processing (TIP) [code]

2016

Oracle Based Active Set Algorithm for Scalable Elastic Net Subspace Clustering

Chong You, Chun-Guang Li, Daniel P. Robinson, René Vidal

IEEE Conference in Computer Vision and Pattern Recognition (CVPR)  (Oral presentation with acceptance rate 3.9%) [talk] [slides] [poster] [matlab code] [python code] 

Scalable Sparse Subspace Clustering by Orthogonal Matching Pursuit

Chong You, Daniel P. Robinson, René Vidal

IEEE Conference in Computer Vision and Pattern Recognition (CVPR)  (Oral presentation with acceptance rate 3.9%)[talk] [slides] [poster] [matlab code] [python code]

A Divide-and-Conquer Framework for Large-Scale Subspace Clustering

Chong You, Claire Donnat, Daniel P. Robinson, René Vidal

Asilomar Conference on Signals, Systems, and Computers

2015

Geometric Conditions for Subspace-Sparse Recovery

Chong You,  René Vidal

International Conference in Machine Learning (ICML)[talk] [poster]