Accepted author manuscript, 1.03 MB, PDF document
Available under license: CC BY: Creative Commons Attribution 4.0 International License
Research output: Contribution to Journal/Magazine › Conference article › peer-review
<mark>Journal publication date</mark> | 12/12/2023 |
---|---|
<mark>Journal</mark> | Advances in Neural Information Processing Systems |
Volume | 36 |
Publication Status | Published |
<mark>Original language</mark> | English |
Event | 37th Conference on Neural Information Processing Systems, NeurIPS 2023 - New Orleans, United States Duration: 10/12/2023 → 16/12/2023 |
Conference | 37th Conference on Neural Information Processing Systems, NeurIPS 2023 |
---|---|
Country/Territory | United States |
City | New Orleans |
Period | 10/12/23 → 16/12/23 |
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.