Abstract | ||
---|---|---|
Monte Carlo sampling in high-dimensional, low-sample settings is important in many machine learning tasks. We improve current methods for sampling in Euclidean spaces by avoiding independence, and instead consider ways to couple samples. We show fundamental connections to optimal transport theory, leading to novel sampling algorithms, and providing new theoretical grounding for existing strategies. We compare our new strategies against prior methods for improving sample efficiency, including quasi-Monte Carlo, by studying discrepancy. We explore our findings empirically, and observe benefits of our sampling schemes for reinforcement learning and generative modelling. |
Year | Venue | Keywords |
---|---|---|
2018 | ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018) | reinforcement learning,euclidean spaces,monte carlo sampling,sampling algorithms,geometrically coupled monte carlo sampling |
Field | DocType | Volume |
Monte Carlo method,Mathematical optimization,Transport theory,Computer science,Artificial intelligence,Sampling (statistics),Euclidean geometry,Generative grammar,Gibbs sampling,Machine learning,Reinforcement learning | Conference | 31 |
ISSN | Citations | PageRank |
1049-5258 | 2 | 0.38 |
References | Authors | |
0 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Rowland, Mark | 1 | 49 | 7.39 |
Krzysztof Choromanski | 2 | 124 | 23.56 |
Chalus, François | 3 | 2 | 0.38 |
Aldo Pacchiano | 4 | 10 | 11.62 |
Tamás Sarlós | 5 | 477 | 25.73 |
Richard E. Turner | 6 | 322 | 37.95 |
Adrian Weller | 7 | 141 | 27.59 |