English
Related papers

Related papers: A Paired Autoencoder Framework for Inverse Problem…

200 papers

Autoencoder-based learning has emerged as a staple for disciplining representations in unsupervised and semi-supervised settings. This paper analyzes a framework for improving generalization in a purely supervised setting, where the target…

Machine Learning · Statistics 2020-01-24 Daniel Jarrett , Mihaela van der Schaar

In the Bayesian approach to inverse problems, data are often informative, relative to the prior, only on a low-dimensional subspace of the parameter space. Significant computational savings can be achieved by using this subspace to…

Numerical Analysis · Mathematics 2015-07-07 Alessio Spantini , Antti Solonen , Tiangang Cui , James Martin , Luis Tenorio , Youssef Marzouk

In numerous practical applications, especially in medical image reconstruction, it is often infeasible to obtain a large ensemble of ground-truth/measurement pairs for supervised learning. Therefore, it is imperative to develop unsupervised…

Image and Video Processing · Electrical Eng. & Systems 2021-03-31 Subhadip Mukherjee , Ozan Öktem , Carola-Bibiane Schönlieb

This work addresses image restoration tasks through the lens of inverse problems using unpaired datasets. In contrast to traditional approaches -- which typically assume full knowledge of the forward model or access to paired degraded and…

Computer Vision and Pattern Recognition · Computer Science 2025-06-18 Giacomo Meanti , Thomas Ryckeboer , Michael Arbel , Julien Mairal

Inverse design in science and engineering involves determining optimal design parameters that achieve desired performance outcomes, a process often hindered by the complexity and high dimensionality of design spaces, leading to significant…

Machine Learning · Computer Science 2025-02-24 Luka Grbcic , Juliane Müller , Wibe Albert de Jong

There has been a lot of recent interest in designing neural network models to estimate a distribution from a set of examples. We introduce a simple modification for autoencoder neural networks that yields powerful generative models. Our…

Machine Learning · Computer Science 2015-06-08 Mathieu Germain , Karol Gregor , Iain Murray , Hugo Larochelle

Feedforward neural networks are widely used as universal predictive models to fit data distribution. Common gradient-based learning, however, suffers from many drawbacks making the training process ineffective and time-consuming.…

Machine Learning · Computer Science 2021-07-06 Grzegorz Dudek

Inverse problems, i.e., estimating parameters of physical models from experimental data, are ubiquitous in science and engineering. The Bayesian formulation is the gold standard because it alleviates ill-posedness issues and quantifies…

Machine Learning · Statistics 2024-05-28 Sharmila Karumuri , Ilias Bilionis

We formulate learning of a binary autoencoder as a biconvex optimization problem which learns from the pairwise correlations between encoded and decoded bits. Among all possible algorithms that use this information, ours finds the…

Machine Learning · Computer Science 2016-11-08 Akshay Balsubramani

Inverse problems are the task of calibrating models to match data. They play a pivotal role in diverse engineering applications by allowing practitioners to align models with reality. In many applications, engineers and scientists do not…

Machine Learning · Computer Science 2026-03-05 Pengyu Zhang , Arnaud Vadeboncoeur , Alex Glyn-Davies , Mark Girolami

Autoencoders are powerful machine learning models used to compress information from multiple data sources. However, autoencoders, like all artificial neural networks, are often unidentifiable and uninterpretable. This research focuses on…

This paper introduces a novel two-stage machine learning-based surrogate modeling framework to address inverse problems in scientific and engineering fields. In the first stage of the proposed framework, a machine learning model termed the…

Machine Learning · Computer Science 2024-01-05 Farhad Pourkamali-Anaraki , Jamal F. Husseini , Evan J. Pineda , Brett A. Bednarcyk , Scott E. Stapleton

Enforcing complex (e.g., nonconvex) operational constraints is a critical challenge in real-world learning and control systems. However, existing methods struggle to efficiently enforce general classes of constraints. To address this, we…

Machine Learning · Computer Science 2026-04-07 Maria Chzhen , Priya L. Donti

We present a novel approach for constrained Bayesian inference. Unlike current methods, our approach does not require convexity of the constraint set. We reduce the constrained variational inference to a parametric optimization over the…

Machine Learning · Computer Science 2013-09-27 Oluwasanmi Koyejo , Joydeep Ghosh

Bayesian inverse problems use observed data to update a prior probability distribution for an unknown state or parameter of a scientific system to a posterior distribution conditioned on the data. In many applications, the unknown parameter…

Numerical Analysis · Mathematics 2026-05-12 Josie König , Elizabeth Qian , Melina A. Freitag

We consider amortized Bayesian inference for nonlinear inverse problems in settings where only samples from the joint distribution of parameters and observations are available. Classical methods such as Markov chain Monte Carlo require…

Numerical Analysis · Mathematics 2026-05-19 Hojjat Kaveh , Ricardo Baptista , Andrew M. Stuart

Learning-based methods for inverse problems, adapting to the data's inherent structure, have become ubiquitous in the last decade. Besides empirical investigations of their often remarkable performance, an increasing number of works…

Numerical Analysis · Mathematics 2023-07-21 Clemens Arndt , Sören Dittmer , Nick Heilenkötter , Meira Iske , Tobias Kluth , Judith Nickel

One fundamental problem when solving inverse problems is how to find regularization parameters. This article considers solving this problem using data-driven bilevel optimization, i.e. we consider the adaptive learning of the regularization…

Statistics Theory · Mathematics 2021-01-08 Neil K. Chada , Claudia Schillings , Xin T. Tong , Simon Weissmann

Self-supervised learning can significantly improve the performance of downstream tasks, however, the dimensions of learned representations normally lack explicit physical meanings. In this work, we propose a novel self-supervised approach…

Audio and Speech Processing · Electrical Eng. & Systems 2022-01-19 Yifan Sun , Xihong Wu

Common domain shift problem formulations consider the integration of multiple source domains, or the target domain during training. Regarding the generalization of machine learning models between different car interiors, we formulate the…

Computer Vision and Pattern Recognition · Computer Science 2021-05-10 Steve Dias Da Cruz , Bertram Taetz , Oliver Wasenmüller , Thomas Stifter , Didier Stricker