Learning Rate Free Sampling in Constrained Domains

Sharrock, Louis and Mackey, Lester and Nemeth, Christopher (2023) Learning Rate Free Sampling in Constrained Domains. Advances in Neural Information Processing Systems, 36. ISSN 1049-5258

[thumbnail of NeurIPS-2023-learning-rate-free-sampling-in-constrained-domains-Paper-Conference]
Text (NeurIPS-2023-learning-rate-free-sampling-in-constrained-domains-Paper-Conference) - Published Version
Available under License Creative Commons Attribution.

Download (0B)
[thumbnail of NeurIPS-2023-learning-rate-free-sampling-in-constrained-domains-Paper-Conference]
Text (NeurIPS-2023-learning-rate-free-sampling-in-constrained-domains-Paper-Conference)
NeurIPS-2023-learning-rate-free-sampling-in-constrained-domains-Paper-Conference.pdf - Accepted Version
Available under License Creative Commons Attribution.

Download (1MB)

Abstract

We introduce a suite of new particle-based algorithms for sampling in constrained domains which are entirely learning rate free. Our approach leverages coin betting ideas from convex optimisation, and the viewpoint of constrained sampling as a mirrored optimisation problem on the space of probability measures. Based on this viewpoint, we also introduce a unifying framework for several existing constrained sampling algorithms, including mirrored Langevin dynamics and mirrored Stein variational gradient descent. We demonstrate the performance of our algorithms on a range of numerical examples, including sampling from targets on the simplex, sampling with fairness constraints, and constrained sampling problems in post-selection inference. Our results indicate that our algorithms achieve competitive performance with existing constrained sampling methods, without the need to tune any hyperparameters.

Item Type:
Journal Article
Journal or Publication Title:
Advances in Neural Information Processing Systems
Additional Information:
Publisher Copyright: © 2023 Neural information processing systems foundation. All rights reserved.
Uncontrolled Keywords:
/dk/atira/pure/subjectarea/asjc/1700/1705
Subjects:
?? computer networks and communicationsinformation systemssignal processing ??
ID Code:
219971
Deposited By:
Deposited On:
16 May 2024 13:35
Refereed?:
Yes
Published?:
Published
Last Modified:
19 Jun 2024 00:51