Avatar

Huan Li

lihuanss AT nuaa.edu.cn

Associate Professor

Nankai University

Biography

“I am an associate professor at Nankai University. I have graduated from Peking University (PKU) supervised by Prof. Zhouchen Lin. Before studying in PKU, I obtained my bachelor degree from Central South University in 2011.

Interests

  • Optimization
  • Machine learning

Education

  • Ph.D in Computer Engineering, 2015-2019

    Peking University

  • MSc in Computer Engineering, 2011-2014

    Peking University

  • BSc in Medical Information, 2007-2011

    Central South University

Publications @ZERO Lab

Restarted Nonconvex Accelerated Gradient Descent: No More Polylogarithmic Factor in the O(ε−7/4) Complexity. JMLR, 2023.

This paper studies accelerated gradient methods for nonconvex optimization with Lipschitz continuous gradient and Hessian. We propose …
PDF

Alternating Direction Method of Multipliers for Machine Learning. Springer Singapore, 2022.

Machine learning heavily relies on optimization algorithms to solve its learning models. Constrained problems constitute a major type …
PDF

Variance Reduced EXTRA and DIGing and Their Optimal Acceleration for Strongly Convex Decentralized Optimization. JMLR, 2022.

We study stochastic decentralized optimization for the problem of training machine learning models with large-scale distributed data. …
Huan Li , Zhouchen Lin , Yongchun Fang
PDF

Decentralized Accelerated Gradient Methods With Increasing Penalty Parameters. IEEE T. Signal Processing, 2020.

In this paper, we study the communication and (sub)gradient computation costs in distributed optimization and give a sharp complexity …
Huan Li , Cong Fang , Wotao Yin , Zhouchen Lin
PDF DOI

Accelerated First-Order Optimization Algorithms for Machine Learning. P IEEE, 2020.

Numerical optimization serves as one of the pillars of machine learning. To meet the demands of big data applications, lots of efforts …
PDF

Accelerated Optimization for Machine Learning: First-Order Algorithms. Springer Singapore, 2020.

This book on optimization includes forewords by Michael I. Jordan, Zongben Xu and Zhi-Quan Luo. Machine learning relies heavily on …
PDF

On the Complexity Analysis of the Primal Solutions for the Accelerated Randomized Dual Coordinate Ascent. JMLR, 2020.

Our study aims to give the convergence rate analysis of the primal solutions for the accelerated randomized dual coordinate ascent.
PDF

Revisiting EXTRA for Smooth Distributed Optimization. SIOPT, 2020.

EXTRA is a popular method for dencentralized distributed optimization and has broad applications. This paper revisits EXTRA. First, we …
PDF DOI

Accelerated Alternating Direction Method of Multipliers:An Optimal O(1/K) Nonergodic Analysis. JSC, 2019.

The Alternating Direction Method of Multipliers (ADMM) is widely used for linearly constrained convex problems. It is proven to have an …
PDF

Accelerated Alternating Direction Method of Multipliers: an Optimal O(1/K) Nonergodic Analysis. J SCI COMPUT, 2019.

The Alternating Direction Method of Multipliers (ADMM) is widely used for linearly constrained convex problems. It is proven to have an …
PDF

Construction of Incoherent Dictionaries via Direct Babel Function Minimization. ACML, 2018.

We propose an augmented Lagrange multiplier based algorithm to solve this nonconvex and nonsmooth problem with the convergence …
PDF

Optimization Algorithm Inspired Deep Neural Network Structure Design. ACML, 2018.

In this paper, we propose the hypothesis that the neural network structure design can be inspired by optimization algorithms and a …
PDF

Optimized Projections for Compressed Sensing via Direct Mutual Coherence Minimization. SP, 2018.

We propose to find an optimal projection matrix by minimizing the mutual coherence of PD directly to recover the signal from a small …
PDF

Provable Accelerated Gradient Method for Nonconvex Low Rank Optimization. ML, 2017.

Optimization over low rank matrices has broad applications in machine learning. For large scale problems, an attractive heuristic is to …
PDF

Fast Proximal Linearized Alternating Direction Method of Multiplier with Parallel Splitting. AAAI, 2016.

We propose the Fast Proximal Augmented Lagragian Method (Fast PALM) which achieves the convergence rate O(1/K^2), compared with O(1/K) …
Canyi Lu , Huan Li , Zhouchen Lin , Shuicheng Yan
PDF supp

Accelerated Proximal Gradient Methods for Nonconvex Programming. NIPS, 2015.

We extend APG for general nonconvex and nonsmooth programs by introducing a monitor that satisfies the sufficient descent property
PDF Code supp

Linearized Alternating Direction Method with Parallel Splitting and Adaptive Penalty for Separable Convex Programs in Machine Learning. ML, 2014.

We propose LADM with parallel splitting and adaptive penalty (LADMPSAP) to solve multi-block separable convex programs efficiently. We …
PDF DOI