paper-with-me

홈 › Papers

Deep neural networks can stably solve high-dimensional, noisy, non-linear inverse problems

2022-06-02 · Andrés Felipe Lerma Pineda, Philipp Christian Petersen

We study the problem of reconstructing solutions of inverse problems when only noisy measurements are available. We assume that the problem can be modeled with an infinite-dimensional forward operator that is not continuously invertible. Then, we restrict this forward operator to finite-dimensional spaces so that the inverse is Lipschitz continuous. For the inverse operator, we demonstrate that there exists a neural network which is a robust-to-noise approximation of the operator. In addition, we show that these neural networks can be learned from appropriately perturbed training data. We demonstrate the admissibility of this approach to a wide range of inverse problems of practical interest. Numerical examples are given that support the theoretical findings.

📄 PDF Abstract BibTeX arXiv:2206.00934

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Sparse High-Dimensional Linear Regression. Algorithmic Barriers and a Local Search Algorithm

2017-11-14 · David Gamarnik, Ilias Zadik

We consider a sparse high dimensional regression model where the goal is to recover a $k$-sparse unknown vector $\beta^*$ from $n$ noisy linear observations of the form $Y=X\beta^*+W \in \mathbb{R}^n$ where $X \in \mathb…

Denoisingregression

Polar Deconvolution of Mixed Signals

2020-10-14 · Zhenan Fan, Halyun Jeong, Babhru Joshi, Michael P. Friedlander

The signal demixing problem seeks to separate a superposition of multiple signals into its constituent components. This paper studies a two-stage approach that first decompresses and subsequently deconvolves the noisy an…

CoShaRP: A Convex Program for Single-shot Tomographic Shape Sensing

2020-12-08 · Ajinkya Kadu, Tristan van Leeuwen, K. Joost Batenburg

We introduce single-shot X-ray tomography that aims to estimate the target image from a single cone-beam projection measurement. This linear inverse problem is extremely under-determined since the measurements are far fe…

Physics-informed deep learning and compressive collocation for high-dimensional diffusion-reaction equations: practical existence theory and numerics

2024-06-03 · Simone Brugiapaglia, Nick Dexter, Samir Karam, Weiqi Wang

On the forefront of scientific computing, Deep Learning (DL), i.e., machine learning with Deep Neural Networks (DNNs), has emerged a powerful new tool for solving Partial Differential Equations (PDEs). It has been observ…

Adapt in the Wild: Test-Time Entropy Minimization with Sharpness and Feature Regularization

2025-09-05 · Shuaicheng Niu, Guohao Chen, Deyu Chen, Yifan Zhang 외 arxiv

Test-time adaptation (TTA) may fail to improve or even harm the model performance when test data have: 1) mixed distribution shifts, 2) small batch sizes, 3) online imbalanced label distribution shifts. This is often a k…

Test-time Adaptation