Taming the Interacting Particle Langevin Algorithm: The Superlinear case
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909633638039552 |
|---|---|
| author | Johnston, Tim Makras, Nikolaos Sabanis, Sotirios |
| author_facet | Johnston, Tim Makras, Nikolaos Sabanis, Sotirios |
| contents | Recent advances in stochastic optimization have yielded the interacting particle Langevin algorithm (IPLA), which leverages the notion of interacting particle systems (IPS) to efficiently sample from approximate posterior densities. This becomes particularly crucial in relation to the framework of Expectation-Maximization (EM), where the E-step is computationally challenging or even intractable. Although prior research has focused on scenarios involving convex cases with gradients of log densities that grow at most linearly, our work extends this framework to include polynomial growth. Taming techniques are employed to produce an explicit discretization scheme that yields a new class of stable, under such non-linearities, algorithms which are called tamed interacting particle Langevin algorithms (tIPLA). We obtain non-asymptotic convergence error estimates in Wasserstein-2 distance for the new class under the best known rate. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_19587 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Taming the Interacting Particle Langevin Algorithm: The Superlinear case Johnston, Tim Makras, Nikolaos Sabanis, Sotirios Probability Computation Machine Learning 60H35 (Primary), 62D05 (Secondary) Recent advances in stochastic optimization have yielded the interacting particle Langevin algorithm (IPLA), which leverages the notion of interacting particle systems (IPS) to efficiently sample from approximate posterior densities. This becomes particularly crucial in relation to the framework of Expectation-Maximization (EM), where the E-step is computationally challenging or even intractable. Although prior research has focused on scenarios involving convex cases with gradients of log densities that grow at most linearly, our work extends this framework to include polynomial growth. Taming techniques are employed to produce an explicit discretization scheme that yields a new class of stable, under such non-linearities, algorithms which are called tamed interacting particle Langevin algorithms (tIPLA). We obtain non-asymptotic convergence error estimates in Wasserstein-2 distance for the new class under the best known rate. |
| title | Taming the Interacting Particle Langevin Algorithm: The Superlinear case |
| topic | Probability Computation Machine Learning 60H35 (Primary), 62D05 (Secondary) |
| url | https://arxiv.org/abs/2403.19587 |