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

Text (NeurIPS-2023-learning-rate-free-sampling-in-constrained-domains-Paper-Conference) - Published Version
Available under License Creative Commons Attribution.
Download (0B)

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.