Learning Rate Free Bayesian Inference in Constrained Domains

Sharrock, Louis and Mackey, Lester and Nemeth, Christopher (2023) Learning Rate Free Bayesian Inference in Constrained Domains. Other. UNSPECIFIED.

[thumbnail of 2305.14943v1]
Text (2305.14943v1)
2305.14943v1.pdf

Download (1MB)

Abstract

We introduce a suite of new particle-based algorithms for sampling on 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:
Monograph (Other)
Subjects:
?? stat.mlcs.lgstat.me ??
ID Code:
195378
Deposited By:
Deposited On:
06 Jun 2023 11:10
Refereed?:
No
Published?:
Published
Last Modified:
23 Sep 2024 00:55