Stochastic Flows and Geometric Optimization on the Orthogonal Group
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
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.
Mar-30-2020
- Country:
- Oceania > Australia
- New South Wales > Sydney (0.04)
- North America
- United States
- New York
- Richmond County > New York City (0.04)
- Queens County > New York City (0.04)
- New York County > New York City (0.04)
- Kings County > New York City (0.04)
- Bronx County > New York City (0.04)
- Onondaga County > Syracuse (0.04)
- Nevada > Clark County
- Las Vegas (0.04)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- Hawaii > Honolulu County
- Honolulu (0.04)
- California
- San Francisco County > San Francisco (0.14)
- Santa Clara County > San Jose (0.04)
- Monterey County > Monterey (0.04)
- Alameda County > Berkeley (0.04)
- Los Angeles County
- Los Angeles (0.14)
- Long Beach (0.04)
- New York
- Canada
- Quebec > Montreal (0.04)
- British Columbia > Metro Vancouver Regional District
- Vancouver (0.04)
- Alberta > Census Division No. 15
- Improvement District No. 9 > Banff (0.04)
- United States
- Europe
- United Kingdom > England
- Cambridgeshire > Cambridge (0.14)
- Oxfordshire > Oxford (0.04)
- Greater London > London (0.04)
- Sweden > Stockholm
- Stockholm (0.04)
- United Kingdom > England
- Asia
- Middle East > Qatar
- Japan > Kyūshū & Okinawa
- Okinawa (0.04)
- China > Beijing
- Beijing (0.04)
- Oceania > Australia
- Genre:
- Research Report (1.00)
- Technology: