Back to Search Start Over

Stochastic Flows and Geometric Optimization on the Orthogonal Group

Authors :
Choromanski, Krzysztof
Cheikhi, David
Davis, Jared
Likhosherstov, Valerii
Nazaret, Achille
Bahamou, Achraf
Song, Xingyou
Akarte, Mrugank
Parker-Holder, Jack
Bergquist, Jacob
Gao, Yuan
Pacchiano, Aldo
Sarlos, Tamas
Weller, Adrian
Sindhwani, Vikas
Publication Year :
2020

Abstract

We present a new class of stochastic, geometrically-driven optimization algorithms on the orthogonal group $O(d)$ and naturally reductive homogeneous manifolds obtained from the action of the rotation group $SO(d)$. We theoretically and experimentally demonstrate that our methods can be applied in various fields of machine learning including deep, convolutional and recurrent neural networks, reinforcement learning, normalizing flows and metric learning. We show an intriguing connection between efficient stochastic optimization on the orthogonal group and graph theory (e.g. matching problem, partition functions over graphs, graph-coloring). We leverage the theory of Lie groups and provide theoretical results for the designed class of algorithms. We demonstrate broad applicability of our methods by showing strong performance on the seemingly unrelated tasks of learning world models to obtain stable policies for the most difficult $\mathrm{Humanoid}$ agent from $\mathrm{OpenAI}$ $\mathrm{Gym}$ and improving convolutional neural networks.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2003.13563
Document Type :
Working Paper