Laixi Shi
Ph.D. Candidate
Department of Electrical and Computer Engineering, Carnegie Mellon Unviersity, Pittsburgh, United States
Email: laixis AT andrew DOT cmu DOT edu
[ Google Scholar ]At present, I'm a Ph.D. student in the Department of Electrical and Computer Engineering of Carnegie Mellon University. I am fortunate to be advised by Prof.Yuejie Chi. I received my bachelor's degree from Electronic Engineering, Tsinghua University in July 2018. Here is my short CV.
My research interests include signal processing, nonconvex optimization, high-dimensional statistical estimation and reinforcement learning, ranging from theory to applications.
News & Updates
[2022/09/28-12/16] Student researcher in Google Research, Brain Team.
[2022/05/15] One paper accepted at International Conference on Machine Learning (ICML), 2022.
[2021/09/28] One paper accepted as NeurIPS Spotlight.
Preprints & Publications
Distributionally Robust Model-Based Offline Reinforcement Learning with Near-Optimal Sample Complexity
Laixi Shi and Yuejie Chi
[Paper]
Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation
Peide Huang, Mengdi Xu, Jiacheng Zhu, Laixi Shi, Fei Fang, Ding Zhao
Conference on Neural Information Processing Systems (NeurIPS), 2022
[Paper]
Settling the Sample Complexity of Model-Based Offline Reinforcement Learning
Gen Li, Laixi Shi, Yuxin Chen, Yuejie Chi, Yuting Wei
[Paper]
Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity
Laixi Shi, Gen Li, Yuting Wei, Yuxin Chen, Yuejie Chi.
International Conference on Machine Learning (ICML), 2022.
[Paper]
Latent Goal Allocation for Multi-Agent Goal-Conditioned Self-Supervised Imitation Learning
Laixi Shi*, Peide Huang*, Rui Chen*
NeurIPS Workshop on Bayesian Deep Learning, 2021 ( * = equal contribution)
[Paper]
Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning
Gen Li, Laixi Shi, Yuxin Chen, Yuejie Chi
Information and Inference: A Journal of the IMA. A short version accepted as [NeurIPS Spotlight] Conference on Neural Information Processing Systems (NeurIPS), 2021
Manifold Gradient Descent Solves Multi-channel Sparse Blind Deconvolution Provably and Efficiently
Laixi Shi, Yuejie Chi
IEEE Transactions on Information Theory, vol. 67, no. 7, pp. 4784-4811, 2021. A short conference version has been accepted by International Conference on Acoustics, Speech, and Signal ProcessingInternational Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020.
Projects
Non-Wearable Three-Dimensional Display and Interaction Cube Based on Multi-Screen
Nov 1, 2016. Advisor: Huimin Ma, Tsinghua University, Beijing, China.
We designed a real-time virtual reality cubic interaction metaphor, arranged 5 LED panels into a cube to create a 3D object illusion, utilizing binocular vision to track user’s eyes and rendering the perspective of each screen to fit the user’s eyes positions.
[Video]
Collaborative Distributed Formation System based on Cars/Unmanned Aerial Vehicle
Jul 18, 2016. Advisor: Yuan Shen, Tsinghua University, Beijing, China
We developed a multiple robot collaborative localization and navigation system using a self-made mobile robot platform. The robots in our system are equipped with a wireless distributed localization system based on UWB(Ultra Wide Band), which enables them automatically to form a pre-defined formation with mutual localization information. (Image from my collaborator Wenhao Ding)
Air Hockey Robot
Jun 13, 2015, Tsinghua University, Beijing, China
We built a robot to play air-hockey game with human, which is a popular table game. This robot consists of a bird-view camera (capturing the images of moving ball) and an executive arm (a striking device with two degrees of freedom). (Image from my collaborator Wenhao Ding)