Grey-box Bayesian Optimization by Peter Frazier
A Google TechTalk, presented by Peter I. Frazier, 2021/06/08
ABSTRACT: Bayesian optimization is a powerful tool for optimizing time-consuming-to-evaluate non-convex derivative-free objective functions. While BayesOpt has historically been deployed as a black-box optimizer, recent advances show considerable gains by "peeking inside the box". For example, when tuning hyperparameters in deep neural networks to minimize validation error, state-of-the-art BayesOpt tuning methods leverage the ability to stop training early, restart previously paused training, perform training and testing on a strict subset of the available data, and warm-start from previously tuned network architectures. We describe new "grey box" Bayesian optimization methods that selectively exploit problem structure to deliver state-of-the-art performance. We then briefly describe applications of these methods to tuning deep neural networks, inverse reinforcement learning and calibrating physics-based simulators to observational data.
About the speaker: Peter Frazier is the Eleanor and Howard Morgan Professor of Operations Research and Information Engineering at Cornell University. He is also a Staff Data Scientist at Uber. He leads Cornell's COVID-19 Mathematical Modeling Team, which designed Cornell's testing strategy to support safe in-person education during the pandemic. His academic research during more ordinary times is in Bayesian optimization, incentive design for social learning and multi-armed bandits. At Uber, he managed UberPool's data science group and currently helps to design Uber's pricing systems.
Видео Grey-box Bayesian Optimization by Peter Frazier канала Google TechTalks
ABSTRACT: Bayesian optimization is a powerful tool for optimizing time-consuming-to-evaluate non-convex derivative-free objective functions. While BayesOpt has historically been deployed as a black-box optimizer, recent advances show considerable gains by "peeking inside the box". For example, when tuning hyperparameters in deep neural networks to minimize validation error, state-of-the-art BayesOpt tuning methods leverage the ability to stop training early, restart previously paused training, perform training and testing on a strict subset of the available data, and warm-start from previously tuned network architectures. We describe new "grey box" Bayesian optimization methods that selectively exploit problem structure to deliver state-of-the-art performance. We then briefly describe applications of these methods to tuning deep neural networks, inverse reinforcement learning and calibrating physics-based simulators to observational data.
About the speaker: Peter Frazier is the Eleanor and Howard Morgan Professor of Operations Research and Information Engineering at Cornell University. He is also a Staff Data Scientist at Uber. He leads Cornell's COVID-19 Mathematical Modeling Team, which designed Cornell's testing strategy to support safe in-person education during the pandemic. His academic research during more ordinary times is in Bayesian optimization, incentive design for social learning and multi-armed bandits. At Uber, he managed UberPool's data science group and currently helps to design Uber's pricing systems.
Видео Grey-box Bayesian Optimization by Peter Frazier канала Google TechTalks
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Learning to Optimize High Dimensional Optimization ProblemsBayesian OptimizationGilles Louppe | Bayesian optimization with Scikit-Optimize2. Bayesian OptimizationBayesian Optimization (Bayes Opt): Easy explanation of popular hyperparameter tuning methodBayesian Optimization with Gradients - NIPS 2017Bayes theorem, the geometry of changing beliefsMicroNugget: What is Black vs Gray vs White Box Testing?Christian Tjandraatmadja Constrained Discrete Black-Box Optimization using Mixed-Integer ProgrammingGPSS2019 - Introduction to Bayesian OptimisationBayesian Hyperparameter OptimizationAutomated Tuning of the JVM with Bayesian OptimizationPhilipp Hennig: Bayesian Optimisation is Probabilistic NumericsNando de Freitas: Bayesian OptimizationHyperparameter Optimization - The Math of Intelligence #7Introduction to Bayesian Optimization, Javier GonzalezBayesian Optimization with Gradients (NIPS 2017 Oral)Moritz Neeb - Bayesian Optimization and it's application to Neural NetworksML Tutorial: Bayesian Optimization (Cedric Archambeau)