CUED Publications database

Geometrically coupled monte carlo sampling

Rowland, M and Choromanski, K and Chalus, F and Pacchiano, A and Sarlós, T and Turner, RE and Weller, A (2018) Geometrically coupled monte carlo sampling. In: NeurIPS 2018, -- to -- pp. 195-206..

Full text not available from this repository.


© 2018 Curran Associates Inc..All rights reserved. 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.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Divisions: Div F > Computational and Biological Learning
Depositing User: Cron Job
Date Deposited: 20 Sep 2019 20:02
Last Modified: 08 Jul 2021 06:26