Adaptive sampling using variational autoencoder and reinforcement learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rasheed, Adil, Shahly, Mikael Aleksander Jansen, Aftab, Muhammad Faisal
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915651038216192
author Rasheed, Adil
Shahly, Mikael Aleksander Jansen
Aftab, Muhammad Faisal
author_facet Rasheed, Adil
Shahly, Mikael Aleksander Jansen
Aftab, Muhammad Faisal
contents Compressed sensing enables sparse sampling but relies on generic bases and random measurements, limiting efficiency and reconstruction quality. Optimal sensor placement uses historcal data to design tailored sampling patterns, yet its fixed, linear bases cannot adapt to nonlinear or sample-specific variations. Generative model-based compressed sensing improves reconstruction using deep generative priors but still employs suboptimal random sampling. We propose an adaptive sparse sensing framework that couples a variational autoencoder prior with reinforcement learning to select measurements sequentially. Experiments show that this approach outperforms CS, OSP, and Generative model-based reconstruction from sparse measurements.
format Preprint
id arxiv_https___arxiv_org_abs_2512_03525
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Adaptive sampling using variational autoencoder and reinforcement learning
Rasheed, Adil
Shahly, Mikael Aleksander Jansen
Aftab, Muhammad Faisal
Machine Learning
Compressed sensing enables sparse sampling but relies on generic bases and random measurements, limiting efficiency and reconstruction quality. Optimal sensor placement uses historcal data to design tailored sampling patterns, yet its fixed, linear bases cannot adapt to nonlinear or sample-specific variations. Generative model-based compressed sensing improves reconstruction using deep generative priors but still employs suboptimal random sampling. We propose an adaptive sparse sensing framework that couples a variational autoencoder prior with reinforcement learning to select measurements sequentially. Experiments show that this approach outperforms CS, OSP, and Generative model-based reconstruction from sparse measurements.
title Adaptive sampling using variational autoencoder and reinforcement learning
topic Machine Learning
url https://arxiv.org/abs/2512.03525