Doob's Lagrangian: A Sample-Efficient Variational Approach to Transition Path Sampling
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916514950545408 |
|---|---|
| author | Du, Yuanqi Plainer, Michael Brekelmans, Rob Duan, Chenru Noé, Frank Gomes, Carla P. Aspuru-Guzik, Alán Neklyudov, Kirill |
| author_facet | Du, Yuanqi Plainer, Michael Brekelmans, Rob Duan, Chenru Noé, Frank Gomes, Carla P. Aspuru-Guzik, Alán Neklyudov, Kirill |
| contents | Rare event sampling in dynamical systems is a fundamental problem arising in the natural sciences, which poses significant computational challenges due to an exponentially large space of trajectories. For settings where the dynamical system of interest follows a Brownian motion with known drift, the question of conditioning the process to reach a given endpoint or desired rare event is definitively answered by Doob's h-transform. However, the naive estimation of this transform is infeasible, as it requires simulating sufficiently many forward trajectories to estimate rare event probabilities. In this work, we propose a variational formulation of Doob's h-transform as an optimization problem over trajectories between a given initial point and the desired ending point. To solve this optimization, we propose a simulation-free training objective with a model parameterization that imposes the desired boundary conditions by design. Our approach significantly reduces the search space over trajectories and avoids expensive trajectory simulation and inefficient importance sampling estimators which are required in existing methods. We demonstrate the ability of our method to find feasible transition paths on real-world molecular simulation and protein folding tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_07974 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Doob's Lagrangian: A Sample-Efficient Variational Approach to Transition Path Sampling Du, Yuanqi Plainer, Michael Brekelmans, Rob Duan, Chenru Noé, Frank Gomes, Carla P. Aspuru-Guzik, Alán Neklyudov, Kirill Machine Learning Artificial Intelligence Biological Physics Chemical Physics Rare event sampling in dynamical systems is a fundamental problem arising in the natural sciences, which poses significant computational challenges due to an exponentially large space of trajectories. For settings where the dynamical system of interest follows a Brownian motion with known drift, the question of conditioning the process to reach a given endpoint or desired rare event is definitively answered by Doob's h-transform. However, the naive estimation of this transform is infeasible, as it requires simulating sufficiently many forward trajectories to estimate rare event probabilities. In this work, we propose a variational formulation of Doob's h-transform as an optimization problem over trajectories between a given initial point and the desired ending point. To solve this optimization, we propose a simulation-free training objective with a model parameterization that imposes the desired boundary conditions by design. Our approach significantly reduces the search space over trajectories and avoids expensive trajectory simulation and inefficient importance sampling estimators which are required in existing methods. We demonstrate the ability of our method to find feasible transition paths on real-world molecular simulation and protein folding tasks. |
| title | Doob's Lagrangian: A Sample-Efficient Variational Approach to Transition Path Sampling |
| topic | Machine Learning Artificial Intelligence Biological Physics Chemical Physics |
| url | https://arxiv.org/abs/2410.07974 |