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 Qi Lei

Qi Lei

Going Beyond Linear RL: Sample Efficient Neural Function Approximation


Jul 14, 2021
Baihe Huang, Kaixuan Huang, Sham M. Kakade, Jason D. Lee, Qi Lei, Runzhe Wang, Jiaqi Yang

Figure 1 for Going Beyond Linear RL: Sample Efficient Neural Function Approximation
Figure 2 for Going Beyond Linear RL: Sample Efficient Neural Function Approximation

  Access Paper or Ask Questions

Optimal Gradient-based Algorithms for Non-concave Bandit Optimization


Jul 09, 2021
Baihe Huang, Kaixuan Huang, Sham M. Kakade, Jason D. Lee, Qi Lei, Runzhe Wang, Jiaqi Yang

Figure 1 for Optimal Gradient-based Algorithms for Non-concave Bandit Optimization
Figure 2 for Optimal Gradient-based Algorithms for Non-concave Bandit Optimization

  Access Paper or Ask Questions

A Short Note on the Relationship of Information Gain and Eluder Dimension


Jul 06, 2021
Kaixuan Huang, Sham M. Kakade, Jason D. Lee, Qi Lei


  Access Paper or Ask Questions

Near-Optimal Linear Regression under Distribution Shift


Jun 23, 2021
Qi Lei, Wei Hu, Jason D. Lee

Figure 1 for Near-Optimal Linear Regression under Distribution Shift
Figure 2 for Near-Optimal Linear Regression under Distribution Shift
Figure 3 for Near-Optimal Linear Regression under Distribution Shift
Figure 4 for Near-Optimal Linear Regression under Distribution Shift
* ICML 2021 
  Access Paper or Ask Questions

How Fine-Tuning Allows for Effective Meta-Learning


May 05, 2021
Kurtland Chua, Qi Lei, Jason D. Lee

Figure 1 for How Fine-Tuning Allows for Effective Meta-Learning
Figure 2 for How Fine-Tuning Allows for Effective Meta-Learning

  Access Paper or Ask Questions

A Theory of Label Propagation for Subpopulation Shift


Feb 22, 2021
Tianle Cai, Ruiqi Gao, Jason D. Lee, Qi Lei

Figure 1 for A Theory of Label Propagation for Subpopulation Shift
Figure 2 for A Theory of Label Propagation for Subpopulation Shift
Figure 3 for A Theory of Label Propagation for Subpopulation Shift
Figure 4 for A Theory of Label Propagation for Subpopulation Shift

  Access Paper or Ask Questions

Fast Convergence of Langevin Dynamics on Manifold: Geodesics meet Log-Sobolev


Oct 11, 2020
Xiao Wang, Qi Lei, Ioannis Panageas

Figure 1 for Fast Convergence of Langevin Dynamics on Manifold: Geodesics meet Log-Sobolev
Figure 2 for Fast Convergence of Langevin Dynamics on Manifold: Geodesics meet Log-Sobolev
Figure 3 for Fast Convergence of Langevin Dynamics on Manifold: Geodesics meet Log-Sobolev

  Access Paper or Ask Questions

Predicting What You Already Know Helps: Provable Self-Supervised Learning


Aug 03, 2020
Jason D. Lee, Qi Lei, Nikunj Saunshi, Jiacheng Zhuo

Figure 1 for Predicting What You Already Know Helps: Provable Self-Supervised Learning
Figure 2 for Predicting What You Already Know Helps: Provable Self-Supervised Learning
Figure 3 for Predicting What You Already Know Helps: Provable Self-Supervised Learning

  Access Paper or Ask Questions

Steepest Descent Neural Architecture Optimization: Escaping Local Optimum with Signed Neural Splitting


Mar 23, 2020
Lemeng Wu, Mao Ye, Qi Lei, Jason D. Lee, Qiang Liu

Figure 1 for Steepest Descent Neural Architecture Optimization: Escaping Local Optimum with Signed Neural Splitting
Figure 2 for Steepest Descent Neural Architecture Optimization: Escaping Local Optimum with Signed Neural Splitting
Figure 3 for Steepest Descent Neural Architecture Optimization: Escaping Local Optimum with Signed Neural Splitting
Figure 4 for Steepest Descent Neural Architecture Optimization: Escaping Local Optimum with Signed Neural Splitting

  Access Paper or Ask Questions

Compressed Sensing with Invertible Generative Models and Dependent Noise


Mar 18, 2020
Jay Whang, Qi Lei, Alexandros G. Dimakis

Figure 1 for Compressed Sensing with Invertible Generative Models and Dependent Noise
Figure 2 for Compressed Sensing with Invertible Generative Models and Dependent Noise
Figure 3 for Compressed Sensing with Invertible Generative Models and Dependent Noise
Figure 4 for Compressed Sensing with Invertible Generative Models and Dependent Noise

  Access Paper or Ask Questions

Few-Shot Learning via Learning the Representation, Provably


Feb 21, 2020
Simon S. Du, Wei Hu, Sham M. Kakade, Jason D. Lee, Qi Lei


  Access Paper or Ask Questions

Last iterate convergence in no-regret learning: constrained min-max optimization for convex-concave landscapes


Feb 21, 2020
Qi Lei, Sai Ganesh Nagarajan, Ioannis Panageas, Xiao Wang

Figure 1 for Last iterate convergence in no-regret learning: constrained min-max optimization for convex-concave landscapes
Figure 2 for Last iterate convergence in no-regret learning: constrained min-max optimization for convex-concave landscapes
Figure 3 for Last iterate convergence in no-regret learning: constrained min-max optimization for convex-concave landscapes
Figure 4 for Last iterate convergence in no-regret learning: constrained min-max optimization for convex-concave landscapes

  Access Paper or Ask Questions

CAT: Customized Adversarial Training for Improved Robustness


Feb 17, 2020
Minhao Cheng, Qi Lei, Pin-Yu Chen, Inderjit Dhillon, Cho-Jui Hsieh

Figure 1 for CAT: Customized Adversarial Training for Improved Robustness
Figure 2 for CAT: Customized Adversarial Training for Improved Robustness
Figure 3 for CAT: Customized Adversarial Training for Improved Robustness
Figure 4 for CAT: Customized Adversarial Training for Improved Robustness

  Access Paper or Ask Questions

Communication-Efficient Asynchronous Stochastic Frank-Wolfe over Nuclear-norm Balls


Oct 17, 2019
Jiacheng Zhuo, Qi Lei, Alexandros G. Dimakis, Constantine Caramanis

Figure 1 for Communication-Efficient Asynchronous Stochastic Frank-Wolfe over Nuclear-norm Balls
Figure 2 for Communication-Efficient Asynchronous Stochastic Frank-Wolfe over Nuclear-norm Balls
Figure 3 for Communication-Efficient Asynchronous Stochastic Frank-Wolfe over Nuclear-norm Balls
Figure 4 for Communication-Efficient Asynchronous Stochastic Frank-Wolfe over Nuclear-norm Balls

  Access Paper or Ask Questions

SGD Learns One-Layer Networks in WGANs


Oct 15, 2019
Qi Lei, Jason D. Lee, Alexandros G. Dimakis, Constantinos Daskalakis

Figure 1 for SGD Learns One-Layer Networks in WGANs
Figure 2 for SGD Learns One-Layer Networks in WGANs
* 21 pages, 4 figures 
  Access Paper or Ask Questions

Inverting Deep Generative models, One layer at a time


Jun 19, 2019
Qi Lei, Ajil Jalal, Inderjit S. Dhillon, Alexandros G. Dimakis

Figure 1 for Inverting Deep Generative models, One layer at a time
Figure 2 for Inverting Deep Generative models, One layer at a time
Figure 3 for Inverting Deep Generative models, One layer at a time
Figure 4 for Inverting Deep Generative models, One layer at a time

  Access Paper or Ask Questions

Primal-Dual Block Frank-Wolfe


Jun 06, 2019
Qi Lei, Jiacheng Zhuo, Constantine Caramanis, Inderjit S. Dhillon, Alexandros G. Dimakis

Figure 1 for Primal-Dual Block Frank-Wolfe
Figure 2 for Primal-Dual Block Frank-Wolfe
Figure 3 for Primal-Dual Block Frank-Wolfe
Figure 4 for Primal-Dual Block Frank-Wolfe

  Access Paper or Ask Questions

Discrete Attacks and Submodular Optimization with Applications to Text Classification


Dec 01, 2018
Qi Lei, Lingfei Wu, Pin-Yu Chen, Alexandros G. Dimakis, Inderjit S. Dhillon, Michael Witbrock

Figure 1 for Discrete Attacks and Submodular Optimization with Applications to Text Classification
Figure 2 for Discrete Attacks and Submodular Optimization with Applications to Text Classification
Figure 3 for Discrete Attacks and Submodular Optimization with Applications to Text Classification
Figure 4 for Discrete Attacks and Submodular Optimization with Applications to Text Classification

  Access Paper or Ask Questions

Random Warping Series: A Random Features Method for Time-Series Embedding


Sep 14, 2018
Lingfei Wu, Ian En-Hsu Yen, Jinfeng Yi, Fangli Xu, Qi Lei, Michael Witbrock

Figure 1 for Random Warping Series: A Random Features Method for Time-Series Embedding
Figure 2 for Random Warping Series: A Random Features Method for Time-Series Embedding
Figure 3 for Random Warping Series: A Random Features Method for Time-Series Embedding
Figure 4 for Random Warping Series: A Random Features Method for Time-Series Embedding
* AIStats18, Oral Paper, Add code link for generating RWS 
  Access Paper or Ask Questions

Hessian-based Analysis of Large Batch Training and Robustness to Adversaries


Jun 18, 2018
Zhewei Yao, Amir Gholami, Qi Lei, Kurt Keutzer, Michael W. Mahoney

Figure 1 for Hessian-based Analysis of Large Batch Training and Robustness to Adversaries
Figure 2 for Hessian-based Analysis of Large Batch Training and Robustness to Adversaries
Figure 3 for Hessian-based Analysis of Large Batch Training and Robustness to Adversaries
Figure 4 for Hessian-based Analysis of Large Batch Training and Robustness to Adversaries
* 23 pages, 16 figures 
  Access Paper or Ask Questions

Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization


Mar 25, 2018
Jiong Zhang, Qi Lei, Inderjit S. Dhillon

Figure 1 for Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization
Figure 2 for Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization
Figure 3 for Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization
Figure 4 for Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization
* main text 13 pages, 22 pages including reference and appendix 
  Access Paper or Ask Questions

Negative-Unlabeled Tensor Factorization for Location Category Inference from Highly Inaccurate Mobility Data


May 24, 2017
Jinfeng Yi, Qi Lei, Wesley Gifford, Ji Liu, Junchi Yan

Figure 1 for Negative-Unlabeled Tensor Factorization for Location Category Inference from Highly Inaccurate Mobility Data
Figure 2 for Negative-Unlabeled Tensor Factorization for Location Category Inference from Highly Inaccurate Mobility Data
Figure 3 for Negative-Unlabeled Tensor Factorization for Location Category Inference from Highly Inaccurate Mobility Data
Figure 4 for Negative-Unlabeled Tensor Factorization for Location Category Inference from Highly Inaccurate Mobility Data

  Access Paper or Ask Questions

Similarity Preserving Representation Learning for Time Series Analysis


Mar 09, 2017
Qi Lei, Jinfeng Yi, Roman Vaculin, Lingfei Wu, Inderjit S. Dhillon

Figure 1 for Similarity Preserving Representation Learning for Time Series Analysis
Figure 2 for Similarity Preserving Representation Learning for Time Series Analysis
Figure 3 for Similarity Preserving Representation Learning for Time Series Analysis
Figure 4 for Similarity Preserving Representation Learning for Time Series Analysis

  Access Paper or Ask Questions

Gradient Coding


Mar 08, 2017
Rashish Tandon, Qi Lei, Alexandros G. Dimakis, Nikos Karampatziakis

Figure 1 for Gradient Coding
Figure 2 for Gradient Coding
Figure 3 for Gradient Coding
Figure 4 for Gradient Coding

  Access Paper or Ask Questions

A Greedy Approach for Budgeted Maximum Inner Product Search


Oct 11, 2016
Hsiang-Fu Yu, Cho-Jui Hsieh, Qi Lei, Inderjit S. Dhillon

Figure 1 for A Greedy Approach for Budgeted Maximum Inner Product Search
Figure 2 for A Greedy Approach for Budgeted Maximum Inner Product Search
Figure 3 for A Greedy Approach for Budgeted Maximum Inner Product Search
Figure 4 for A Greedy Approach for Budgeted Maximum Inner Product Search

  Access Paper or Ask Questions

Coordinate Descent Methods for Symmetric Nonnegative Matrix Factorization


May 31, 2016
Arnaud Vandaele, Nicolas Gillis, Qi Lei, Kai Zhong, Inderjit Dhillon

Figure 1 for Coordinate Descent Methods for Symmetric Nonnegative Matrix Factorization
Figure 2 for Coordinate Descent Methods for Symmetric Nonnegative Matrix Factorization
Figure 3 for Coordinate Descent Methods for Symmetric Nonnegative Matrix Factorization
Figure 4 for Coordinate Descent Methods for Symmetric Nonnegative Matrix Factorization
* IEEE Transactions on Signal Processing 64 (21), pp. 5571-5584, 2016 
 * 25 pages, 5 figures, 7 tables. Main changes: comparison with another symNMF algorithm (namely, BetaSNMF), and correction of an error in the convergence proof 
  Access Paper or Ask Questions