Timezone: »

Learn2Hop: Learned Optimization on Rough Landscapes
Amil Merchant · Luke Metz · Samuel Schoenholz · Ekin Dogus Cubuk

Thu Jul 22 09:00 PM -- 11:00 PM (PDT) @

Optimization of non-convex loss surfaces containing many local minima remains a critical problem in a variety of domains, including operations research, informatics, and material design. Yet, current techniques either require extremely high iteration counts or a large number of random restarts for good performance. In this work, we propose adapting recent developments in meta-learning to these many-minima problems by learning the optimization algorithm for various loss landscapes. We focus on problems from atomic structural optimization---finding low energy configurations of many-atom systems---including widely studied models such as bimetallic clusters and disordered silicon. We find that our optimizer learns a hopping behavior which enables efficient exploration and improves the rate of low energy minima discovery. Finally, our learned optimizers show promising generalization with efficiency gains on never before seen tasks (e.g. new elements or compositions). Code is available at https://learn2hop.page.link/github.

Author Information

Amil Merchant (Google)
Luke Metz (Google Brain)
Samuel Schoenholz (Google Brain)
Ekin Dogus Cubuk (Google Brain)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors