Solving Inverse Physics Problems with Score Matching
- URL: http://arxiv.org/abs/2301.10250v2
- Date: Tue, 5 Dec 2023 12:06:18 GMT
- Title: Solving Inverse Physics Problems with Score Matching
- Authors: Benjamin J. Holzschuh, Simona Vegetti, Nils Thuerey
- Abstract summary: We propose to solve inverse problems involving the temporal evolution of physics systems by leveraging recent advances from diffusion models.
Our method moves the system's current state backward in time step by step by combining an approximate inverse physics simulator and a learned correction function.
- Score: 20.315933488318986
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We propose to solve inverse problems involving the temporal evolution of
physics systems by leveraging recent advances from diffusion models. Our method
moves the system's current state backward in time step by step by combining an
approximate inverse physics simulator and a learned correction function. A
central insight of our work is that training the learned correction with a
single-step loss is equivalent to a score matching objective, while recursively
predicting longer parts of the trajectory during training relates to maximum
likelihood training of a corresponding probability flow. We highlight the
advantages of our algorithm compared to standard denoising score matching and
implicit score matching, as well as fully learned baselines for a wide range of
inverse physics problems. The resulting inverse solver has excellent accuracy
and temporal stability and, in contrast to other learned inverse solvers,
allows for sampling the posterior of the solutions.
Related papers
- A Guide to Stochastic Optimisation for Large-Scale Inverse Problems [4.926711494319977]
optimisation algorithms are the de facto standard for machine learning with large amounts of data.
We provide a comprehensive account of the state-of-the-art in optimisation from the viewpoint of inverse problems.
We focus on the challenges for optimisation that are unique and are not commonly encountered in machine learning.
arXiv Detail & Related papers (2024-06-10T15:02:30Z) - Improving Diffusion Models for Inverse Problems Using Optimal Posterior Covariance [52.093434664236014]
Recent diffusion models provide a promising zero-shot solution to noisy linear inverse problems without retraining for specific inverse problems.
Inspired by this finding, we propose to improve recent methods by using more principled covariance determined by maximum likelihood estimation.
arXiv Detail & Related papers (2024-02-03T13:35:39Z) - Adaptive operator learning for infinite-dimensional Bayesian inverse problems [7.716833952167609]
We develop an adaptive operator learning framework that can reduce modeling error gradually by forcing the surrogate to be accurate in local areas.
We present a rigorous convergence guarantee in the linear case using the UKI framework.
The numerical results show that our method can significantly reduce computational costs while maintaining inversion accuracy.
arXiv Detail & Related papers (2023-10-27T01:50:33Z) - Learning Iterative Robust Transformation Synchronization [71.73273007900717]
We propose to use graph neural networks (GNNs) to learn transformation synchronization.
In this work, we avoid handcrafting robust loss functions, and propose to use graph neural networks (GNNs) to learn transformation synchronization.
arXiv Detail & Related papers (2021-11-01T07:03:14Z) - Deep Feedback Inverse Problem Solver [141.26041463617963]
We present an efficient, effective, and generic approach towards solving inverse problems.
We leverage the feedback signal provided by the forward process and learn an iterative update model.
Our approach does not have any restrictions on the forward process; it does not require any prior knowledge either.
arXiv Detail & Related papers (2021-01-19T16:49:06Z) - Total Deep Variation: A Stable Regularizer for Inverse Problems [71.90933869570914]
We introduce the data-driven general-purpose total deep variation regularizer.
In its core, a convolutional neural network extracts local features on multiple scales and in successive blocks.
We achieve state-of-the-art results for numerous imaging tasks.
arXiv Detail & Related papers (2020-06-15T21:54:15Z) - Sparse recovery by reduced variance stochastic approximation [5.672132510411465]
We discuss application of iterative quadratic optimization routines to the problem of sparse signal recovery from noisy observation.
We show how one can straightforwardly enhance reliability of the corresponding solution by using Median-of-Means like techniques.
arXiv Detail & Related papers (2020-06-11T12:31:20Z) - Joint learning of variational representations and solvers for inverse
problems with partially-observed data [13.984814587222811]
In this paper, we design an end-to-end framework allowing to learn actual variational frameworks for inverse problems in a supervised setting.
The variational cost and the gradient-based solver are both stated as neural networks using automatic differentiation for the latter.
This leads to a data-driven discovery of variational models.
arXiv Detail & Related papers (2020-06-05T19:53:34Z) - Neural Control Variates [71.42768823631918]
We show that a set of neural networks can face the challenge of finding a good approximation of the integrand.
We derive a theoretically optimal, variance-minimizing loss function, and propose an alternative, composite loss for stable online training in practice.
Specifically, we show that the learned light-field approximation is of sufficient quality for high-order bounces, allowing us to omit the error correction and thereby dramatically reduce the noise at the cost of negligible visible bias.
arXiv Detail & Related papers (2020-06-02T11:17:55Z) - Solving Inverse Problems with a Flow-based Noise Model [100.18560761392692]
We study image inverse problems with a normalizing flow prior.
Our formulation views the solution as the maximum a posteriori estimate of the image conditioned on the measurements.
We empirically validate the efficacy of our method on various inverse problems, including compressed sensing with quantized measurements and denoising with highly structured noise patterns.
arXiv Detail & Related papers (2020-03-18T08:33:49Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.