Molei Tao 陶默雷
Georgia Institute of Technology
Molei Tao received B.S. in Math & Physics in 2006 from Tsinghua Univ. and Ph.D. in Control & Dynamical Systems with a minor in Physics in 2011 from Caltech. Afterwards, he worked as a postdoc in Computing & Mathematical Sciences at Caltech from 2011 to 2012, and then as a Courant Instructor at NYU from 2012 to 2014. From 2014 on, he has been an assistant, and then associate professor in School of Math at Georgia Tech. He is a recipient of W.P. Carey Ph.D. Prize in Applied Mathematics (2011), American Control Conference Best Student Paper Finalist (2013), NSF CAREER Award (2019), AISTATS Best Paper Award (2020), IEEE EFTF-IFCS Best Student Paper Finalist (2021), Cullen-Peck Scholar Award (2022), GT-Emory AI.Humanity Award (2023), a Plenary Speaker at Georgia Scientific Computing Symposium (2024), a Keynote Speaker at (2024) International Conference on Scientific Computing and Machine Learning, and SONY Faculty Innovation Award (2024).
Abstract
Machine learning in non-Euclidean spaces have been rapidly attracting attention in recent years, and this talk will give some examples of progress on its mathematical and algorithmic foundations. A sequence of developments that eventually leads to non-Euclidean generative modeling will be reported.
More precisely, I will begin with variational optimization, which, together with delicate interplays between continuous- and discrete-time dynamics, enables the construction of momentum-accelerated algorithms that optimize functions defined on manifolds. Selected applications, namely a generic improvement of Transformer, and a low-dim. approximation of high-dim. optimal transport distance, will be described. Then I will turn the optimization dynamics into an algorithm that samples from probability distributions on Lie groups. If time permits, the performance of this sampler will also be quantified, without log-concavity condition or its common relaxations. Finally, I will describe how this sampler can lead to a structurally-pleasant diffusion generative model that allows users to, given training data that follow any latent statistical distribution on a Lie group, generate more data exactly on the same manifold that follow the same distribution.
