COIL: Constrained Optimization in Learned Latent Space

Embed Cite Participate Recommend

Constrained optimization problems can be difficult because their search spaces have properties not conducive to search, e.g., multimodality, discontinuities, or deception. Peter Bentley discusses the Constrained Optimization in Latent Space (COIL), which uses a VAE to generate a learned latent representation from a dataset comprising samples from the valid region of the search space according to a constraint, thus enabling the optimizer to find the objective in the new space defined by the learned representation.

Read the Study

Image courtesy of interviewee

Log-in or Sign-up to Faculti
Currently viewing as guest. You have insight(s) remaining for this month.

Leave a Reply

Your email address will not be published.

Copyright © Faculti Media Limited 2023. All rights reserved.
Recommend Faculti to your librarian

Thousands of engaging insights, delivered at the world's leading institutions. 
Librarians welcome and value students, faculty and staff recommendations, and we aim to facilitate these suggestions in an impactful way.

error: