Laixi Shi - Carnegie Mellon University


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

[2021/11/01] One paper accepted at NeurIPS Workshop on Bayesian Deep Learning.

[2021/09/28] One paper accepted as NeurIPS Spotlight.

[2020/05/18-08/21] Internship in Mitsubishi Electric Research Laboratories (MERL) from May to August.

Preprints & Publications

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

[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, Yuantao Gu, Yuejie Chi
[NeurIPS Spotlight] Conference on Neural Information Processing Systems (NeurIPS), 2021

[Paper] [Talk] [Slides] [Poster]

Robust camera pose estimation for image stitching

Laixi Shi, Dehong Liu, Jay Thornton
IEEE International Conference on Image Processing (ICIP), 2021.

[Paper] [Slides]

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.

[Paper] [Slides] [Poster]

Fusion-Based Digital Image Correlation Framework for Strain Measurement

Laixi Shi, Dehong Liu, Masaki Umeda, and Norihiko Hana
International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2021.

[Paper] [Slides]

Device-free Multiple People Localization through Floor Vibration

Laixi Shi, Mostafa Mirshekari, Jonathon Fagert, Yuejie Chi, Hae Young Noh, Pei Zhang, and Shijia Pan
First ACM Workshop on Device-Free Human Sensing, 2019.

[Paper] [Slides]

Micro Hand Gesture Recognition System Using Ultrasonic Active Sensing

Yu Sang, Laixi Shi, Yimin Liu
IEEE Access, vol. 6, pp. 49339-49347, 2018.

[Paper] [Video]

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 System based on cars/Unmanned Aerial Vehicle Coordinated Formation Design

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)