Yuejie Chi

Yuejie Chi Sense of Wonder Group Endowed Professor in AI Systems Department of Electrical and Computer Engineering Machine Learning Department and CyLab (by courtesy) Carnegie Mellon University Short Bio  /  Google Scholar

I am the Sense of Wonder Group Endowed Professor of Electrical and Computer Engineering in AI Systems at Carnegie Mellon University. I am also an affiliated faculty member with the Machine Learning Department and CyLab. My department homepage is here.

My research interests lie in the theoretical and algorithmic foundations of data science, machine learning, signal processing and inverse problems, with applications in sensing, imaging, decision making, and societal systems, broadly defined. The problems my group studies are often interdisciplinary in nature, lying at the intersection of statistics, learning, optimization, and sensing. My current focus is on improving the efficiency and reliability of generative AI and reinforcement learning, driven by data-intensive applications in science and engineering. Specific lines of research topics can be found here.

I have been lucky to receive a couple of awards for my work, including Presidential Early Career Award for Scientists and Engineers (PECASE) from the White House, the highest honor bestowed by the United States Government to outstanding early-career scientists and engineers who show exceptional promise for leadership in science and technology. In 2019, I received the inaugural IEEE Signal Processing Society Early Career Technical Achievement Award for contributions to high-dimensional structured signal processing. In addition, I received SIAM Activity Group on Imaging Science Best Paper Prize, IEEE Signal Processing Society Young Author Best Paper Award, and young investigator awards from several agencies including NSF, ONR and AFOSR. At CMU, I received the College of Engineering Philip and Marsha Dowd Fellowship in 2023, and held the inaugural Robert E. Doherty Career Development Professorship during 2018-2020.

I am an IEEE Fellow (Class of 2023) for contributions to statistical signal processing with low-dimensional structures. [ECE News] [SCS News]

I also had the privilege to deliver plenary, keynote and tutorial talks at several conferences and workshops, with more materials shared here. I was named the Goldsmith Lecturer by IEEE Information Theory Society in 2021, a Distinguished Lecturer by IEEE Signal Processing Society for 2022-2023, and a Distinguished Speaker by ACM for 2023-2026.

Previously I was with the Dept. of Electrical and Computer Engineering and the Dept. of Biomedical Informatics at The Ohio State University until 2017. I completed my Ph.D. in Electrical Engineering from Princeton University in 2012, where I was fortunate to be advised by Prof. Robert Calderbank. I received a M.A. in Electrical Engineering from Princeton University in 2009, and a B.Eng. in Electronic Engineering from Tsinghua University in 2007.

I have an Erdos number of 3.

To prospective students: I have openings for Ph.D. and postdoc positions in my group, working on both mathematical theory and engineering applications for AI and data science. However, I may not be able to respond to all inquiries due to bandwidth.

Upcoming

• Nov. 2024: Plenary Speaker at IEEE Information Theory Workshop (ITW) in Shenzhen, China.

Selected Recent Papers

• Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF [Arxiv]

• Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction, NeurIPS 2024. [Arxiv] [Code]

• Towards Faster Non-Asymptotic Convergence for Diffusion-Based Generative Models, ICLR 2024. [Arxiv]

• The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model, short version at NeurIPS 2023. [Arxiv]

• The Power of Preconditioning in Overparameterized Low-Rank Matrix Sensing, short version at ICML 2023. [Arxiv]

• The Blessing of Heterogeneity in Federated Q-Learning: Linear Speedup and Beyond, short version at ICML 2023. [Arxiv]

• Settling the Sample Complexity of Model-Based Offline Reinforcement Learning, Annals of Statistics, 2024. [Arxiv]

• Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis, Operations Research, 2024. [Arxiv]

• Fast Global Convergence of Natural Policy Gradient Methods with Entropy Regularization, Operations Research, 2022. [Arxiv]

• Scaling and Scalability: Provable Nonconvex Low-Rank Tensor Estimation from Incomplete Measurements, JMLR 2022. [Arxiv]

• Accelerating Ill-Conditioned Low-Rank Matrix Estimation via Scaled Gradient Descent, JMLR 2020. [Arxiv]

Contact

• Office: Porter Hall B25

• Mailing address: 5000 Forbes Ave., Pittsburgh, PA 15213

• Email: first+last at cmu dot edu = first+c at andrew dot cmu dot edu