Learning Rate Free Sampling in Constrained Domains

Autor:	Sharrock, Louis, Mackey, Lester, Nemeth, Christopher
Rok vydání:	2023
Předmět:	Statistics - Machine Learning Computer Science - Machine Learning Statistics - Methodology
Druh dokumentu:	Working Paper
Popis:	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. Comment: Accepted at NeurIPS 2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2305.14943 Zobrazit plný text záznamu View this record from Arxiv