Flow Priors for Linear Inverse Problems via Iterative Corrupted Trajectory Matching

• URL: http://arxiv.org/abs/2405.18816v3
• Date: Fri, 15 Nov 2024 08:10:51 GMT
• Title: Flow Priors for Linear Inverse Problems via Iterative Corrupted Trajectory Matching
• Authors: Yasi Zhang, Peiyu Yu, Yaxuan Zhu, Yingshan Chang, Feng Gao, Ying Nian Wu, Oscar Leong,
• Abstract summary: We propose an iterative algorithm to approximate the MAP estimator efficiently to solve a variety of linear inverse problems. Our algorithm is mathematically justified by the observation that the MAP objective can be approximated by a sum of $N$ local MAP'' objectives. We validate our approach for various linear inverse problems, such as super-resolution, deblurring, inpainting, and compressed sensing.
• Score: 35.77769905072651
• License:
• Abstract: Generative models based on flow matching have attracted significant attention for their simplicity and superior performance in high-resolution image synthesis. By leveraging the instantaneous change-of-variables formula, one can directly compute image likelihoods from a learned flow, making them enticing candidates as priors for downstream tasks such as inverse problems. In particular, a natural approach would be to incorporate such image probabilities in a maximum-a-posteriori (MAP) estimation problem. A major obstacle, however, lies in the slow computation of the log-likelihood, as it requires backpropagating through an ODE solver, which can be prohibitively slow for high-dimensional problems. In this work, we propose an iterative algorithm to approximate the MAP estimator efficiently to solve a variety of linear inverse problems. Our algorithm is mathematically justified by the observation that the MAP objective can be approximated by a sum of $N$ ``local MAP'' objectives, where $N$ is the number of function evaluations. By leveraging Tweedie's formula, we show that we can perform gradient steps to sequentially optimize these objectives. We validate our approach for various linear inverse problems, such as super-resolution, deblurring, inpainting, and compressed sensing, and demonstrate that we can outperform other methods based on flow matching. Code is available at https://github.com/YasminZhang/ICTM.

Related papers

• A Sample Efficient Alternating Minimization-based Algorithm For Robust Phase Retrieval [56.67706781191521]
  In this work, we present a robust phase retrieval problem where the task is to recover an unknown signal. Our proposed oracle avoids the need for computationally spectral descent, using a simple gradient step and outliers.
  arXiv  Detail & Related papers  (2024-09-07T06:37:23Z)
• Inverse Problems with Diffusion Models: A MAP Estimation Perspective [5.002087490888723]
  In Computer, several image restoration tasks such as inpainting, deblurring, and super-resolution can be formally modeled as inverse problems. We propose a MAP estimation framework to model the reverse conditional generation process of a continuous time diffusion model. We use our proposed framework to develop effective algorithms for image restoration.
  arXiv  Detail & Related papers  (2024-07-27T15:41:13Z)
• Fast Screening Rules for Optimal Design via Quadratic Lasso Reformulation [0.135975510645475]
  In this work, we derive safe screening rules that can be used to discard inessential samples. The new tests are much faster to compute, especially for problems involving a parameter space of high dimension. We show how an existing homotopy algorithm to compute the regularization path of the lasso method can be reparametrized with respect to the squared $ell_$-penalty.
  arXiv  Detail & Related papers  (2023-10-13T08:10:46Z)
• Fast Computation of Optimal Transport via Entropy-Regularized Extragradient Methods [75.34939761152587]
  Efficient computation of the optimal transport distance between two distributions serves as an algorithm that empowers various applications. This paper develops a scalable first-order optimization-based method that computes optimal transport to within $varepsilon$ additive accuracy.
  arXiv  Detail & Related papers  (2023-01-30T15:46:39Z)
• Mean Field Approximation for solving QUBO problems [0.0]
  We show that the statistical physics approach and the quantum mechanical approach in the mean field annealing give the same result. Our methods consist of a set of simple gradient-based minimizations with continuous variables, thus easy to simulate.
  arXiv  Detail & Related papers  (2021-06-06T20:35:28Z)
• Bayesian Algorithm Execution: Estimating Computable Properties of Black-box Functions Using Mutual Information [78.78486761923855]
  In many real world problems, we want to infer some property of an expensive black-box function f, given a budget of T function evaluations. We present a procedure, InfoBAX, that sequentially chooses queries that maximize mutual information with respect to the algorithm's output. On these problems, InfoBAX uses up to 500 times fewer queries to f than required by the original algorithm.
  arXiv  Detail & Related papers  (2021-04-19T17:22:11Z)
• Slowly Varying Regression under Sparsity [5.22980614912553]
  We present the framework of slowly hyper regression under sparsity, allowing regression models to exhibit slow and sparse variations. We suggest a procedure that reformulates as a binary convex algorithm. We show that the resulting model outperforms competing formulations in comparable times across various datasets.
  arXiv  Detail & Related papers  (2021-02-22T04:51:44Z)
• Offline Model-Based Optimization via Normalized Maximum Likelihood Estimation [101.22379613810881]
  We consider data-driven optimization problems where one must maximize a function given only queries at a fixed set of points. This problem setting emerges in many domains where function evaluation is a complex and expensive process. We propose a tractable approximation that allows us to scale our method to high-capacity neural network models.
  arXiv  Detail & Related papers  (2021-02-16T06:04:27Z)
• Accelerated Message Passing for Entropy-Regularized MAP Inference [89.15658822319928]
  Maximum a posteriori (MAP) inference in discrete-valued random fields is a fundamental problem in machine learning. Due to the difficulty of this problem, linear programming (LP) relaxations are commonly used to derive specialized message passing algorithms. We present randomized methods for accelerating these algorithms by leveraging techniques that underlie classical accelerated gradient.
  arXiv  Detail & Related papers  (2020-07-01T18:43:32Z)
• Exploiting Higher Order Smoothness in Derivative-free Optimization and Continuous Bandits [99.70167985955352]
  We study the problem of zero-order optimization of a strongly convex function. We consider a randomized approximation of the projected gradient descent algorithm. Our results imply that the zero-order algorithm is nearly optimal in terms of sample complexity and the problem parameters.
  arXiv  Detail & Related papers  (2020-06-14T10:42:23Z)
• Stochastic Optimization for Regularized Wasserstein Estimators [10.194798773447879]
  We introduce an algorithm to solve a regularized version of the problem of Wasserstein estimators gradient, with a time per step which is sublinear in the natural dimensions. We show that this algorithm can be extended to other tasks, including estimation of Wasserstein barycenters.
  arXiv  Detail & Related papers  (2020-02-20T12:04:05Z)

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.