Structured Monte Carlo Sampling for Nonisotropic Distributions via Determinantal Point Processes
Choromanski, Krzysztof, Pacchiano, Aldo, Parker-Holder, Jack, Tang, Yunhao
We propose a new class of structured methods for Monte Carlo (MC) sampling, called DPPMC, designed for high-dimensional nonisotropic distributions where samples are correlated to reduce the variance of the estimator via determinantal point processes. We successfully apply DPPMCs to problems involving nonisotropic distributions arising in guided evolution strategy (GES) methods for RL, CMA-ES techniques and trust region algorithms for blackbox optimization, improving state-of-the-art in all these settings. In particular, we show that DPPMCs drastically improve exploration profiles of the existing evolution strategy algorithms. We further confirm our results, analyzing random feature map estimators for Gaussian mixture kernels. We provide theoretical justification of our empirical results, showing a connection between DPPMCs and structured orthogonal MC methods for isotropic distributions.
May-29-2019
- Country:
- North America
- United States
- Nevada (0.04)
- Washington > King County
- Bellevue (0.04)
- 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)
- Georgia > Fulton County
- Atlanta (0.04)
- California
- San Francisco County > San Francisco (0.14)
- Los Angeles County > Long Beach (0.04)
- Puerto Rico > San Juan
- San Juan (0.04)
- Canada > Quebec
- Montreal (0.04)
- United States
- Europe
- Sweden > Stockholm
- Stockholm (0.04)
- Spain
- Catalonia > Barcelona Province
- Barcelona (0.04)
- Andalusia > Cádiz Province
- Cadiz (0.04)
- Catalonia > Barcelona Province
- Sweden > Stockholm
- Asia
- Middle East > Jordan (0.04)
- Japan > Honshū
- Kansai > Kyoto Prefecture > Kyoto (0.04)
- China > Beijing
- Beijing (0.04)
- North America
- Genre:
- Research Report > New Finding (0.86)
- Technology: