Learning Finite-Dimensional Coding Schemes with Nonlinear Reconstruction Maps

DOI10.1137/18M1234461zbMath1490.68187arXiv1812.09658OpenAlexW2975585678WikidataQ127248267 ScholiaQ127248267MaRDI QIDQ5025792

Maxim Raginsky, Jae-Ho Lee

Publication date: 3 February 2022

Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1812.09658

zbMATH Keywords

generalization boundsrepresentation learninggenerative modelinganalog lossy compression

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Learning and adaptive systems in artificial intelligence (68T05) Signal theory (characterization, reconstruction, filtering, etc.) (94A12) Coding and information theory (compaction, compression, models of communication, encoding schemes, etc.) (aspects in computer science) (68P30) Rate-distortion theory in information and communication theory (94A34) Optimal transportation (49Q22)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Constructive quantization: approximation by empirical measures
• Oracle inequalities in empirical risk minimization and sparse recovery problems. École d'Été de Probabilités de Saint-Flour XXXVIII-2008.
• Measurable selection theorems for optimization problems
• Sudakov minoration principle and supremum of some processes
• Principal component analysis.
• Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance
• The sizes of compact subsets of Hilbert space and continuity of Gaussian processes
• On the Performance of Clustering in Hilbert Spaces
• Quantization and the method of<tex>k</tex>-means
• On the rate-distortion function of random vectors and stationary sources with mixed distributions
• The minimax distortion redundancy in empirical quantizer design
• Lossy source coding
• 10.1162/153244302760200713
• Neural Network Learning
• Size-independent sample complexity of neural networks
• A Connection Between Score Matching and Denoising Autoencoders
• $K$-Dimensional Coding Schemes in Hilbert Spaces
• Upper and Lower Bounds for Stochastic Processes
• Elements of Information Theory
• The Speed of Mean Glivenko-Cantelli Convergence
• Computation of channel capacity and rate-distortion functions

This page was built for publication: Learning Finite-Dimensional Coding Schemes with Nonlinear Reconstruction Maps