Yuejiao Sun
Ph.D. in Applied Mathematics
University of California, Los Angeles
Email: sunyj + @ + math. + ucla. + edu
[Google Scholar] [GitHub]
Education
University of California, Los Angeles (UCLA): Ph.D. in Applied Mathematics, 2016-2021
Peking University (PKU): B.S. in Mathematics, 2012-2016
Awards
2021 ICASSP Best Student Paper Award
2020 Dissertation Year Fellowship, UCLA
2020 Balbes Award, UCLA Math
2018 AML Summer Research Fellowship, LANL
2016 Excellent Graduate Award (Top 5%), PKU
Experiences
Rensselaer Polytechnic Institute, Troy, NY, US
Visiting scholar, Dec. 2019 - May 2020
Host: Prof. Tianyi Chen
Alibaba US - Damo Academy, Bellevue, WA, US
Research Intern, Jun. 2020 - Sep. 2020
Los Alamos National Lab, Los Alamos, NM, US
Applied Machine Learning Student Intern, Jun. 2018 - Sep. 2018
Research
My research interests include optimization, machine learning and federated computing. I am currently working on optimization methods and theory for large-scale distributed optimization problems.
Publications and Preprints
Tianyi Chen, Yuejiao Sun, and Wotao Yin. "Tighter Analysis of Alternating Stochastic Gradient Method for Stochastic Nested Problems." Advances in Neural Information Processing Systems (NeurIPS), 2021. (Spotlight, top 3% of all submissions) [paper]
Tianyi Chen, Yuejiao Sun, Quan Xiao, and Wotao Yin. "A single-timescale stochastic bilevel optimization method." International Conference on Artificial Intelligence and Statistics (AISTATS), 2022. (Oral, top 2% of all submissions) [paper]
Tianyi Chen, Yuejiao Sun, and Wotao Yin. "Solving Stochastic Compositional Optimization is Nearly as Easy as Solving Stochastic Optimization." IEEE Transactions on Signal Processing (TSP), 2021, the short version of this paper has been recognized as the Best Student Paper Award for ICASSP 2021. [paper]
Tianyi Chen, Ziye Guo, Yuejiao Sun, and Wotao Yin. "CADA: Communication-Adaptive Distributed Adam." AISTATS 2021. [paper]
Tianyi Chen, Yuejiao Sun, and Wotao Yin. "LASG: Lazily Aggregated Stochastic Gradients for Communication-Efficient Distributed Learning." IEEE Transactions on Signal Processing (TSP), 2021 [paper]
Yanli Liu, Yuejiao Sun, and Wotao Yin. "Decentralized Learning with Lazy and Approximate Dual Gradients." IEEE Transactions on Signal Processing (TSP), 2021. [paper]
Tianyi Chen, Xiao Jin, Yuejiao Sun, and Wotao Yin. "VAFL: a Method of Vertical Asynchronous Federated Learning." ICML Workshop on Federated Learning for User Privacy and Data Confidentiality, 2020 [paper]
Tao Sun, Yuejiao Sun, Yangyang Xu and Wotao Yin. "Markov Chain Block Coordinate Descent." Computational Optimization and Applications (2020): 1-27. [paper]
Yifan Chen, Yuejiao Sun, and Wotao Yin. "Run-and-Inspect Method for Nonconvex Optimization and Global Optimality Bounds for R-local Minimizers." Mathematical Programming 176.1-2 (2019): 39-67. [paper][slides]
Tao Sun, Yuejiao Sun, and Wotao Yin. "On Markov Chain Gradient Descent." Advances in Neural Information Processing Systems (NeurIPS) 2018. [paper][poster]
Past Teaching
2020 Spring: MATH 182 - Algorithms
2020 Winter: MATH 118 - Mathematical Methods of Data Theory
2019 Fall : MATH 266A - Applied Ordinary Differential Equations
2019 Spring : MATH 42 - Introduction to Data-Driven Mathematical Modeling
2019 Winter : MATH 170A - Probability Theory
2018 Fall : MATH 170A - Probability Theory
2017 Fall : MATH 3C - Ordinary Differential Equations
2017 Fall : MATH 31B - Integration and Infinite Series
2017 Summer: MATH 32A - Calculus of Several Variables
2017 Spring : MATH 31B - Integration and Infinite Series
2017 Winter: MATH 3B - Calculus for Life Sciences Students
2016 Fall: MATH 1 - Precalculus
Service
Reviewer of NeurIPS
Reviewer of SIAM J. Optimization
Reviewer of Mathematical Programming