Yue Sun
 |
Yue Sun |
About me
I am a software engineer with Microsoft. I graduated as PhD in Department of Electrical Engineering, University of Washington, Seattle supervised by Prof. Maryam Fazel. I graduated as Bachelor of Engineering from Department of Electronics Engineering, Tsinghua University, China. I'm interested in optimization and structured model for control and machine learning.
I joined Google in June-September, 2019, on online optimization algorithm applied in video coding. I joined Nokia Bell Labs in June-August, 2021, on channel estimation for audio echo cancellation.
Here's my CV.
Research Project
Understanding the Role of Representation Dimension in Meta-Learning
Regularization Method in System Identification
Online Learning for Entropy Coding in Next-generation Video Codec
Policy Gradient Descent in Linear System Control and Reinforcement Learning
Perturbed Gradient Descent Method for Non-convex Problem
Phase Retrieval and Low Rank Matrix Completion
Publications
Escaping High-Order Saddles in Policy Optimization for Linear Quadratic Gaussian (LQG) Control. Yang Zheng, Yue Sun, Maryam Fazel and Na Li, submitted to 61st Conference on Decision and Control (CDC 2022).
System Identification via Nuclear Norm Regularization. Yue Sun, Samet Oymak and Maryam Fazel, submitted to IEEE Open Journal of Control Systems (OJ-CSYS).
Towards Sample-Efficient Overparameterized Meta-Learning. Yue Sun, Adhyyan Narang, Ibrahim Gulluk, Samet Oymak and Maryam Fazel, accepted by 35th Conference on Neural Information Processing Systems (NeurIPS 2021).
Learning Optimal Controllers by Policy Gradient: Global Optimality via Convex Parameterization. Yue Sun and Maryam Fazel, in 60th Conference on Decision and Control (CDC 2021).
Sample Efficient Subspace-Based Representations for Nonlinear Meta-Learning. Ibrahim Gulluk, Yue Sun, Samet Oymak and Maryam Fazel, in 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Finite Sample System Identification: Optimal Rates and the Role of Regularization. Yue Sun, Samet Oymak and Maryam Fazel, oral in 2020 Conference of Learning for Dynamics and Control (L4DC). Supplementary
Online Probability Model Estimation For Video Compression. Yue Sun, Jingning Han and Yaowu Xu, in 2020 Data Compression Conference.
Escaping from Saddle Points on Riemannian Manifolds. Yue Sun, Nicolas Flammarion and Maryam Fazel, in Conference on Neural Information Processing Systems (NeurIPS), 2019. Code
Escaping Saddle Points Efficiently in Equality-Constrained Optimization Problems. Yue Sun and Maryam Fazel, in ICML Workshop on Modern Trends in Nonconvex Optimization for Machine Learning, 2018.
Outlier-Robust Recovery of Low-Rank Positive Semidefinite Matrices from Magnitude Measurements. Yue Sun, Yuanxin Li and Yuejie Chi. 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Low-Rank Positive Semidefinite Matrix Recovery From Corrupted Rank-One Measurements. Yuanxin Li, Yue Sun and Yuejie Chi. IEEE Transactions on Signal Processing 65.2 (2017): 397-408.
Teaching
Teaching Assistant of 18Wi: AA/CSE/EE/ME 578 Convex Optimization.