Product Optimization with Adaptive Experimentation at Facebook
Offered By: Meta via YouTube
Course Description
Overview
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.
Syllabus
Optimizing Products with Adaptive Experimentation
The Status Quo: Static Configuration
Personalized Configuration
Many Models Are Compatible with the Data
Bayesian Models Capture Possible Realities
Optimizing HHVM's Just-In-Time Compiler
Ax Empowers Developers to Tune Configurations
Adaptive Experimentation Ecosystem
Adaptive Experimentation in Practice
Bo Torch A Flexible Research Platform for Bayesian Optimization
Taught by
Meta Developers
Related Courses
Addressing Large Hadron Collider Challenges by Machine LearningHigher School of Economics via Coursera Hyperparameter Tuning with Keras Tuner
Coursera Project Network via Coursera Bayesian Optimization with Python
Coursera Project Network via Coursera Automatic Model Tuning in Amazon SageMaker (Traditional Chinese)
Amazon Web Services via AWS Skill Builder Hyperparameter Optimization for Machine Learning
Udemy