Главная
Study mode:
on
1
Optimizing Products with Adaptive Experimentation
2
The Status Quo: Static Configuration
3
Personalized Configuration
4
Many Models Are Compatible with the Data
5
Bayesian Models Capture Possible Realities
6
Optimizing HHVM's Just-In-Time Compiler
7
Ax Empowers Developers to Tune Configurations
8
Adaptive Experimentation Ecosystem
9
Adaptive Experimentation in Practice
10
Bo Torch A Flexible Research Platform for Bayesian Optimization
Description:
Explore adaptive experimentation, an AI-enabled testing approach used by Facebook to optimize products, infrastructure, machine learning models, and marketing campaigns in this 21-minute conference talk from F8 2019. Discover the basic concepts behind adaptive experimentation, its applications, and how to leverage it using Facebook's open-source packages, Ax and botorch. Delve into topics such as static configuration, personalized configuration, Bayesian models, and the optimization of HHVM's Just-In-Time Compiler. Learn how Ax empowers developers to tune configurations and gain insights into the adaptive experimentation ecosystem. Understand the practical implementation of adaptive experimentation and explore Bo Torch, a flexible research platform for Bayesian optimization.

Product Optimization with Adaptive Experimentation at Facebook

Meta
Add to list
0:00 / 0:00