Bayesian sparse reconstruction: a brute-force approach to astronomical imaging and machine learning

Abstract

We present a principled Bayesian framework for signal reconstruction, in which the signal is modelled by basis functions whose number (and form, if required) is determined by the data themselves. This approach is based on a Bayesian interpretation of conventional sparse reconstruction and regularisation techniques, in which sparsity is imposed through priors via Bayesian model selection. We demonstrate our method for noisy 1- and 2-dimensional signals, including astronomical images. Furthermore, by using a product-space approach, the number and type of basis functions can be treated as integer parameters and their posterior distributions sampled directly. We show that order-of-magnitude increases in computational efficiency are possible from this technique compared to calculating the Bayesian evidences separately, and that further computational gains are possible using it in combination with dynamic nested sampling. Our approach can also be readily applied to neural networks, where it allows the network architecture to be determined by the data in a principled Bayesian manner by treating the number of nodes and hidden layers as parameters.

18 pages + appendix, 19 figures, minor updates to text and layout

References in corpus (24)

• MultiNest: an efficient and robust Bayesian inference tool for cosmology and particle physics
• Multimodal nested sampling: an efficient and robust alternative to MCMC methods for astronomical data analysis
• Weight Uncertainty in Neural Networks
• Importance Nested Sampling and the MultiNest Algorithm
• PolyChord: nested sampling for cosmology
• PolyChord: next-generation nested sampling
• Data Mining and Machine Learning in Astronomy
• Dynamic nested sampling: an improved algorithm for parameter estimation and evidence calculation
• The HST eXtreme Deep Field XDF: Combining all ACS and WFC3/IR Data on the HUDF Region into the Deepest Field Ever
• Compressed sensing imaging techniques for radio interferometry
• Compressed Sensing in Astronomy
• Foreground separation methods for satellite observations of the cosmic microwave background
• SKYNET: an efficient and robust neural network training tool for machine learning in astronomy
• Bayesian model selection without evidences: application to the dark energy equation-of-state
• Uncertainty quantification for radio interferometric imaging: I. proximal MCMC methods
• Compressed sensing for wide-field radio interferometric imaging
• Sampling Errors in Nested Sampling Parameter Estimation
• nestcheck: diagnostic tests for nested sampling calculations
• Constraining the dark energy equation of state using Bayes theorem and the Kullback-Leibler divergence
• Maximum-entropy image reconstruction using wavelets
• Towards a framework for testing general relativity with extreme-mass-ratio-inspiral observations
• Bayesian photometric redshifts of blended sources
• Sparse Bayesian Inference and the Temperature Structure of the Solar Corona
• Regularization and Inverse Problems

Cited by in corpus (12)

• dynesty: A Dynamic Nested Sampling Package for Estimating Bayesian Posteriors and Evidences
• Dynamic nested sampling: an improved algorithm for parameter estimation and evidence calculation
• Fast likelihood-free cosmology with neural density estimators and active learning
• Nested sampling for physical scientists
• Dark Energy Survey Year 3 results: curved-sky weak lensing mass map reconstruction
• Quantifying dimensionality: Bayesian cosmological model complexities
• Forming intracluster gas in a galaxy protocluster at a redshift of 2.16
• Label Switching Problem in Bayesian Analysis for Gravitational Wave Astronomy
• Diversity's Double-Edged Sword: Analyzing Race's Effect on Remote Pair Programming Interactions
• Compromise-free Bayesian neural networks
• Hunting for bumps in the margins
• Entropic Dynamics of Networks