ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2003.13563
17
7

Stochastic Flows and Geometric Optimization on the Orthogonal Group

30 March 2020
K. Choromanski
David Cheikhi
Jared Davis
Valerii Likhosherstov
Achille Nazaret
Achraf Bahamou
Xingyou Song
M. Akarte
Jack Parker-Holder
Jacob Bergquist
Yuan Gao
Aldo Pacchiano
Tamás Sarlós
Adrian Weller
Vikas Sindhwani
    AI4CE
ArXivPDFHTML
Abstract

We present a new class of stochastic, geometrically-driven optimization algorithms on the orthogonal group O(d)O(d)O(d) and naturally reductive homogeneous manifolds obtained from the action of the rotation group SO(d)SO(d)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 Humanoid\mathrm{Humanoid}Humanoid agent from OpenAI\mathrm{OpenAI}OpenAI Gym\mathrm{Gym}Gym and improving convolutional neural networks.

View on arXiv
Comments on this paper