Tuesday, October 26, 2021

Designs from Data: Offline Black-Box Optimization via Conservative Training

Recommendable! This seems to be an interesting direction AI research!

"... An appealing alternative is to create designs from data. Instead of requiring active synthesis and querying, can we devise a method that simply examines a large dataset of previously tested designs (e.g., drugs that have been evaluated before [protein folding, hardware design and much more]), and comes up with a new design that is better? We call this offline model-based optimization (offline MBO), and in this post, we discuss offline MBO methods and some recent advances. ..."

Designs from Data: Offline Black-Box Optimization via Conservative Training – The Berkeley Artificial Intelligence Research Blog

No comments: