Consensus-based High Dimensional Global Non-convex Optimization in Machine Learning

Next Friday, January 20, 2023:

Organized by: FAU DCN-AvH, Chair for Dynamics, Control and Numerics – Alexander von Humboldt Professorship at FAU, Friedrich-Alexander-Universität Erlangen-Nürnberg (Germany)
Title: Consensus-based High Dimensional Global Non-convex Optimization in Machine Learning

Speaker: Prof. Dr. Shi Jin
Affiliation: Shanghai Jiao Tong University, China

Abstract. We introduce a stochastic interacting particle consensus system for global optimization of high dimensional non-convex functions. This algorithm does not use gradient of the function thus is suitable for non-smooth functions. We prove, for fully discrete systems, that under dimension-independent conditions on the parameters, with suitable initial data, the algorithms converge to the neighborhood of the global minimum almost surely. We also introduce an Adaptive Moment Estimation (ADAM) based version to significantly improve its performance in high-space dimension.

Slides

Recording/Video:

(Loading this resource…Check again later!)

_
This event on LinkedIn

You might like:
FAU DCN-AvH Seminar by Prof. Dr. Shi Jin (April 1st, 2022): “Quantum algorithms for computing observables of nonlinear partial differential equations

Don’t miss out our upcoming events: Subscribe to the FAU DCN-AvH newsletter!

Connect with us at: