Dynamical Measure Transport and Neural PDE Solvers for Sampling
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916319030411264 |
|---|---|
| author | Sun, Jingtong Berner, Julius Richter, Lorenz Zeinhofer, Marius Müller, Johannes Azizzadenesheli, Kamyar Anandkumar, Anima |
| author_facet | Sun, Jingtong Berner, Julius Richter, Lorenz Zeinhofer, Marius Müller, Johannes Azizzadenesheli, Kamyar Anandkumar, Anima |
| contents | The task of sampling from a probability density can be approached as transporting a tractable density function to the target, known as dynamical measure transport. In this work, we tackle it through a principled unified framework using deterministic or stochastic evolutions described by partial differential equations (PDEs). This framework incorporates prior trajectory-based sampling methods, such as diffusion models or Schrödinger bridges, without relying on the concept of time-reversals. Moreover, it allows us to propose novel numerical methods for solving the transport task and thus sampling from complicated targets without the need for the normalization constant or data samples. We employ physics-informed neural networks (PINNs) to approximate the respective PDE solutions, implying both conceptional and computational advantages. In particular, PINNs allow for simulation- and discretization-free optimization and can be trained very efficiently, leading to significantly better mode coverage in the sampling task compared to alternative methods. Moreover, they can readily be fine-tuned with Gauss-Newton methods to achieve high accuracy in sampling. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_07873 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Dynamical Measure Transport and Neural PDE Solvers for Sampling Sun, Jingtong Berner, Julius Richter, Lorenz Zeinhofer, Marius Müller, Johannes Azizzadenesheli, Kamyar Anandkumar, Anima Machine Learning Dynamical Systems Optimization and Control Probability The task of sampling from a probability density can be approached as transporting a tractable density function to the target, known as dynamical measure transport. In this work, we tackle it through a principled unified framework using deterministic or stochastic evolutions described by partial differential equations (PDEs). This framework incorporates prior trajectory-based sampling methods, such as diffusion models or Schrödinger bridges, without relying on the concept of time-reversals. Moreover, it allows us to propose novel numerical methods for solving the transport task and thus sampling from complicated targets without the need for the normalization constant or data samples. We employ physics-informed neural networks (PINNs) to approximate the respective PDE solutions, implying both conceptional and computational advantages. In particular, PINNs allow for simulation- and discretization-free optimization and can be trained very efficiently, leading to significantly better mode coverage in the sampling task compared to alternative methods. Moreover, they can readily be fine-tuned with Gauss-Newton methods to achieve high accuracy in sampling. |
| title | Dynamical Measure Transport and Neural PDE Solvers for Sampling |
| topic | Machine Learning Dynamical Systems Optimization and Control Probability |
| url | https://arxiv.org/abs/2407.07873 |