Ashwin Renganathan | Sample efficient & Principled Decision making with Expensive Stochastic Oracles

Описание: For our 15th FSML Seminar, we had an excellent and insightful talk from Professor Ashwin Renganathan on scalable uncertainty quantification and optimization methods applied to aerodynamic design problems in multi-objective settings. Check out the very interesting research conducted by his group here! - https://sites.psu.edu/csdl/

Abstract: Modern day engineering decision-making involves one or more computer simulation oracles of an engineered system which can be queried on-demand to learn the system response to control input. Querying simulation oracles, also called “computer experiments”, incur a non-trivial computational cost, which increases with the level of fidelity in the underlying models. For instance, a realistic computational aerodynamic simulation of an aircraft can cost several thousands of CPU hours to compute—anything more than a few dozens of such simulations is prohibitive. Therefore, a central goal of engineering decision-making is to optimally design computer experiments, to maximize the value of information extracted at minimal computational effort.
In this talk, we will address problems anchored in, what we coin, the “decision-making triad” which includes: surrogate modeling, uncertainty quantification (UQ), and numerical optimization/control. Specifically, using variants of a probabilistic surrogate model and a Bayesian decision theoretic framework, we will show that problems in the decision-making triad can be solved in a principled, theoretically sound and, yet (computational) cost-effective manner. We will show demonstrations on applications in computational aerodynamics.

Speaker bio: Ashwin Renganathan is an assistant professor of aerospace engineering at Penn State and holds a joint appointment with the Penn State Institute of Computational and Data Sciences (ICDS). He directs the Computational complex engineered Systems Design Laboratory (CSDL) at Penn State. He is broadly interested in developing novel and scalable computational techniques for surrogate modeling, uncertainty quantification, and numerical optimization, with a focus on aerospace applications. He earned his Ph.D. in aerospace engineering from Georgia Tech and previously completed a postdoctoral appointment in applied mathematics at the Argonne National Laboratory.

00:00 Start
01:59 Introduction
04:51 AI for Science and Engineering
12:33 Kernel Methods and Bayesian Decision Theory
25:50 Bayesian Optimization with Thompson Sampling
31:20 Introduction to Multi-criteria decision making
41:57 Batch Pareto optimal Thomson Sampling (qPOTS)
50:09 Application - Multiobjective aerodynamic design optimization
57:02 Paper and Software, Q&A