Inferring relevant features: from QFT to PCA

DOI10.1142/S0219749918400129MaRDI QIDQ4620312zbMATH OpenOpenAlexFDO

Authors Cédric Bény

Publication date 8 February 2019

Published in International Journal of Quantum Information (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1802.05756

zbMATH Keywords

Bayesian inferenceFisher information metrickernel PCAmachine learningquantum field theory

Mathematics Subject Classification ID

Bayesian inference (62F15) Learning and adaptive systems in artificial intelligence (68T05) Quantum computation (81P68) Model quantum field theories (81T10) Measures of information, entropy (94A17)

Abstract: In many-body physics, renormalization techniques are used to extract aspects of a statistical or quantum state that are relevant at large scale, or for low energy experiments. Recent works have proposed that these features can be formally identified as those perturbations of the states whose distinguishability most resist coarse-graining. Here, we examine whether this same strategy can be used to identify important features of an unlabeled dataset. This approach indeed results in a technique very similar to kernel PCA (principal component analysis), but with a kernel function that is automatically adapted to the data, or "learned". We test this approach on handwritten digits, and find that the most relevant features are significantly better for classification than those obtained from a simple gaussian kernel.

Recommendations

• On relevant dimensions in kernel feature spaces
• PCA meets RG
• Unsupervised features learning for sampled vector fields
• Independent Component Analysis and Blind Signal Separation
• The renormalization group via statistical inference

Cites work

• Holography as deep learning

Cited in

(4)

• PCA meets RG
• Generalized scale behavior and renormalization group for data analysis
• A functional renormalization group for signal detection and stochastic ergodicity breaking
• Functional renormalisation for signal detection: dimensional analysis and dimensional phase transition for nearly continuous spectra effective field theory

This page was built for publication: Inferring relevant features: from QFT to PCA

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4620312)