(Physics informed) Machine Learning and Uncertainty Quantification (2022/2023)
Organizers: OTPF Sabine Andergassen (U. Tübingen), Lukas Exl (WPI), Michael Feischl (TU Wien), PF Shi Jin (Shanghai Jiao Tong Univ.),
Thomas Schrefl (WPI c/o DU Krems)
Talks
| Shi Jin (Inst. Natural Sciences - Shanghai Jiao Tong Univ.) |
WPI Seminar room |
Tue, 7. Feb 23, 14:30 |
| Consensus-based High Dimensional Global Non-convex Optimization in Machine Learning |
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.
|
| Note: External webpage: http://old.ins.sjtu.edu.cn/faculty/jinshi |
- Thematic program: (Physics informed) Machine Learning and Uncertainty Quantification (2022/2023)
|