Lijun Ding



Bio

Lijun Ding

I am a fifth year Ph.D. student in the School of Operations Research and Information Engineering at Cornell University. I am advised by Prof. Yudong Chen and Prof. Madeleine Udell. Prior to joining Cornell in the Fall of 2016, I graduated with a Master of Science in Statistics from the University of Chicago advised by Prof. Lek-Heng Lim . I received a Bachelor of Science in Mathematics and Economics from the Hong Kong University of Scienec and Technology in 2014. I worked as a research intern at the Alibaba DAMO Academy during the summer time of 2019. I am searching for a postdoctoral position now.

My research lies at the intersection of optimization, statistics, and machine learning, where I works on solving large-scale and high dimensional optimization problems. By exploring ideas and techniques such as Frank-Wolfe, strict complementarity, and the leave-one-out argument in these fields, I have been able to design computationally and statistically efficient algorithms for both classical convex optimization problems such as semidefinite programming, and newly arising nonconvex problems.

My work on an optimal-storage approach to SDP using approximate complementarity recently won the Student Paper Prize 2019 of INFORMS Optimization Society.

Research

Low-rank matrix recovery with non-quadratic loss: projected gradient method and regularity projection oracle
Ding, Zhang, and Chen Working Paper (2020)

Revisit of Spectral Bundle Methods: Primal-dual (Sub)linear Convergence Rates
Ding, and Grimmer Working Paper (2020)

kFW: A Frank-Wolfe style algorithm with stronger subproblem oracles
Ding, Fan, and Udell Working Paper (2020)

Spectral Frank-Wolfe Algorithm: Strict Complementarity and Linear Convergence
Ding, Fei, Xu, and Yang International Conference on Machine Learning (ICML) (2020)

On the regularity and conditioning of low rank semidefinite programs
Ding and Udell Submitted (2020)

Bundle Method Sketching for Low Rank Semidefinite Programming
Ding and Grimmer 11th OPT Workshop on Optimization for Machine Learning (OPT2019) (2019)

Factor Group-Sparse Regularization for Efficient Low-Rank Matrix Recovery
Fan, Ding, Chen, and Udell Neural Information Processing Systems Conference (NeurIPS) (2019)

Low-rank matrix recovery with composite optimization: good conditioning and rapid convergence
Charisopoulos, Chen, Davis, Diaz, Ding, and Drusvyatskiy Submitted (2019)

An Optimal-Storage Approach to Semidefinite Programming using Approximate Complementarity
Ding, Yurtsever, Cevher, Tropp, and Udell Submitted (2019)
   Winner of Student Paper Prize 2019 of INFORMS Optimization Society

The Leave-one-out Approach for Matrix Completion: Primal and Dual Analysis
Ding and Chen IEEE Transactions on Information Theory, to appear (2018)

Higher-Order Cone Programming
Ding and Lim Working Paper (2018)

Frank-Wolfe Style Algorithms for Large Scale Optimization
Ding and Udell Large-Scale and Distributed Optimization, Springer (2018)

Talk

Spectral Frank-Wolfe Algorithm: Strict Complementarity and Linear Convergence
International Conference on Machine Learning (ICML) Online 7/2020

An Optimal-Storage Approach to Semidefinite Programming using Approximate Complementarity
SIAM Conference on Computational Science and Engineering Spokane, WA, USA 2/2019

2019 INFORMS Annual Meeting, 10/2019 Seattle, WA, USA 10/2019

The Leave-one-out Approach for Matrix Completion: Primal and Dual Analysis
International Symposium on Mathematical Programming (ISMP) Bordeaux, France 7/2018

Higher-Order Cone Programming
China-Korea International Conference on Matrix Theory with Applications Shanghai, China 12/2016

International Symposium on Mathematical Programming (ISMP) Bordeaux, France 7/2018

Blog

I maintain a blog to post my discoveries of optimization, statistics and probability. These are small, interesting and original results that arising from my studies at Cornell.

Teaching

ORIE 6326
Convex Optimization Teaching Assistant (Spring 2017)

ORIE 5270
Big Data Technologies Instructor (Spring 2019)

ORIE 6125
Computational Methods in Operations Research Instructor (Spring 2019)

Contact

296 Rhodes Hall     •     ld446 at cornell dot edu