Home > Research > Publications & Outputs > Learning Rate Free Sampling in Constrained Domains

Electronic data

Links

View graph of relations

Learning Rate Free Sampling in Constrained Domains

Research output: Contribution to Journal/MagazineConference articlepeer-review

Published

Standard

Learning Rate Free Sampling in Constrained Domains. / Sharrock, Louis; Mackey, Lester; Nemeth, Christopher.
In: Advances in Neural Information Processing Systems, Vol. 36, 12.12.2023.

Research output: Contribution to Journal/MagazineConference articlepeer-review

Harvard

APA

Vancouver

Sharrock L, Mackey L, Nemeth C. Learning Rate Free Sampling in Constrained Domains. Advances in Neural Information Processing Systems. 2023 Dec 12;36.

Author

Sharrock, Louis ; Mackey, Lester ; Nemeth, Christopher. / Learning Rate Free Sampling in Constrained Domains. In: Advances in Neural Information Processing Systems. 2023 ; Vol. 36.

Bibtex

@article{7d0809043c95439cb6fcfb9d5d55dc5b,
title = "Learning Rate Free Sampling in Constrained Domains",
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.",
author = "Louis Sharrock and Lester Mackey and Christopher Nemeth",
note = "Publisher Copyright: {\textcopyright} 2023 Neural information processing systems foundation. All rights reserved.; 37th Conference on Neural Information Processing Systems, NeurIPS 2023 ; Conference date: 10-12-2023 Through 16-12-2023",
year = "2023",
month = dec,
day = "12",
language = "English",
volume = "36",
journal = "Advances in Neural Information Processing Systems",
issn = "1049-5258",

}

RIS

TY - JOUR

T1 - Learning Rate Free Sampling in Constrained Domains

AU - Sharrock, Louis

AU - Mackey, Lester

AU - Nemeth, Christopher

N1 - Publisher Copyright: © 2023 Neural information processing systems foundation. All rights reserved.

PY - 2023/12/12

Y1 - 2023/12/12

N2 - 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.

AB - 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.

M3 - Conference article

AN - SCOPUS:85190256141

VL - 36

JO - Advances in Neural Information Processing Systems

JF - Advances in Neural Information Processing Systems

SN - 1049-5258

T2 - 37th Conference on Neural Information Processing Systems, NeurIPS 2023

Y2 - 10 December 2023 through 16 December 2023

ER -