Guodong Zhang, PhD student in University of Toronto
Sunday, February 20, 2022, 15:00
- 16:00
https://kaust.zoom.us/j/98890162713
Contact Person
In this talk, I will discuss how the use of second-order information – e.g, curvature or covariance – can help in all three problems, yet with vastly different roles in each. First, I will present a noisy quadratic model, which qualitatively predicts scaling properties of a variety of optimizers and in particular suggests that second-order optimization algorithms would extend perfect scaling to much bigger batches. Second, I will show how we can derive and implement scalable and flexible Bayesian inference algorithms from standard second-order optimization algorithms. Third, I will describe a novel second-order algorithm that finds desired equilibria and save us from converging to spurious fixed points in two-player sequential games (i.e. bilevel optimization) or even more general settings. Finally, I will conclude how my research would pave the way towards intelligent machines that can learn from data and experience efficiently, reason about their own decisions, and act in our interests.
Jinchao Xu, Affiliate Professor of Information Sciences and Technology, Penn State University
Wednesday, October 13, 2021, 09:00
- 10:00
Building 9, level 2, Room # 2322
I will give a self-contained introduction to the theory of the neural network function class and its application to image classification and numerical solution of partial differential equations.
Jinchao Xu, Affiliate Professor of Information Sciences and Technology, Penn State University
Tuesday, October 12, 2021, 09:00
- 10:00
BW BUILDING 4 AND 5 Level: 0 Room: AUDITORIUM 0215
I will give a self-contained introduction to the theory of the neural network function class and its application to image classification and numerical solution of partial differential equations.
Jinchao Xu, Affiliate Professor of Information Sciences and Technology, Penn State University
Monday, October 11, 2021, 09:00
- 10:00
BW BUILDING 4 AND 5 Level: 0 Room: AUDITORIUM 0215
I will give a self-contained introduction to the theory of the neural network function class and its application to image classification and numerical solution of partial differential equations.
Didier Barradas-Bautista
Thursday, April 29, 2021, 11:20
- 11:40
https://kaust.zoom.us/j/96464686903
Contact Person

Abstract

Protein-protein interactions drive many important biological events such as infection, re

Thursday, April 29, 2021, 11:00
- 11:20
https://kaust.zoom.us/j/96464686903
Contact Person

Abstract

Quantitative structure-property relationships (QSPRs) using machine learning tools to rel

Michael Berumen
Wednesday, April 28, 2021, 14:20
- 14:40
https://kaust.zoom.us/j/96464686903
Contact Person

Abstract

The Red Sea Development Company (TRSDC), one of Saudi’s premiere GigaProjects, aims to de