Wei Guo (郭纬)

756 W Peachtree St NW
Atlanta, GA 30308
About Me
I am now a second-year Machine Learning Ph.D. student at Georgia Institute of Technology, advised by Professors Yongxin Chen and Molei Tao. Previously, I obtained my Bachelor’s degree in Statistics from the School of Mathematical Sciences, Peking University in 2023, where I was mentored by Professor Cheng Zhang. I was born in Ningbo, Zhejiang, P.R. China in 2001.
My CV can be found here.
Interests
I am broadly interested in fields ranging from statistics, probability, and machine learning:
Statistics: Sampling (Markov Chain Monte Carlo), Computational Statistics, Machine Learning Theory.
Probability: Optimal Transport and Gradient Flow Theory, Applied Stochastic Analysis, Statistical Physics.
Machine Learning: Generative Modeling, Vision and Language Models.
I am particularly interested in the theoretical analysis of sampling algorithms and diffusion/flow models, as well as developing efficient and scalable algorithms and models for sampling and generative modeling. The focus and goal of my research are two-fold: to reveal the fundamental principles behind the success of data-driven algorithms and to use these insights to develop accessible, efficient, and robust approaches for solving real-world problems that are essential and valuable for our society.
I am also interested in la langue française (the French language), vernaculars of Chinese and minority languages in China, linguistics, political science, China’s railway system, civil aviation, architecture, and video games (especially action games such as The Last of Us, Assassin’s Creed, and the Метро (Metro) series). I am also an enthusiast of traveling. Some of my highly recommended destinations possessing profound historical and cultural heritage include Hangzhou, Yangzhou, Datong, Macau, and my hometown Ningbo.
News
Mar 31, 2025 | I will attend ICLR 2025 at Singapore to present the conference paper Provable Benefit of Annealed Langevin Monte Carlo for Non-log-concave Sampling and two papers at the FPI workshop: Fast solvers for discrete diffusion models: Theory and applications of high-order algorithms and Complexity Analysis of Normalizing Constant Estimation: from Jarzynski Equality to Annealed Importance Sampling and beyond. Looking forward to seeing you there! |
---|