Qin Li, Mean field theory in Inverse Problems: from Bayesian inference to overparameterization of networks

Submitted by Ingrid Richter on

The Department of Applied Mathematics weekly seminar is given by scholars and researchers working in applied mathematics, broadly interpreted. 

 


Title: Mean field theory in Inverse Problems: from Bayesian inference to overparameterization of networks
 

Abstract:  Bayesian sampling and neural networks are seemingly two different machine learning areas, but they both deal with many particle systems. In sampling, one evolves a large number of samples (particles) to match a target distribution function, and in optimizing over-parameterized neural networks, one can view neurons particles that feed each other information in the DNN flow. These perspectives allow us to employ mean-field theory, a powerful tool that translates dynamics of many particle system into a partial differential equation (PDE), so rich PDE analysis techniques can be used to understand both the convergence of sampling methods and the zero-loss property of over-parameterization of ResNets. We showcase the use of mean-field theory in these two machine learning areas.

Share