Dimensionality-Dependent Generalization Bounds for k-Dimensional Coding Schemes

DOI10.1162/NECO_a_00872zbMath1474.68315arXiv1601.00238OpenAlexW2223051473WikidataQ39621250 ScholiaQ39621250MaRDI QIDQ5380581

Dacheng Tao, Dong Xu, Tongliang Liu

Publication date: 5 June 2019

Published in: Neural Computation (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1601.00238

Mathematics Subject Classification ID

Computational aspects of data analysis and big data (68T09)

Uses Software

• PDCO
• NeNMF
• Graclus

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Fast rates for empirical vector quantization
• Probability inequalities for empirical processes and a law of the iterated logarithm
• A central limit theorem for k-means clustering
• Sharper bounds for Gaussian and empirical processes
• Nonasymptotic bounds for vector quantization in Hilbert spaces
• On the mathematical foundations of learning
• Sample Complexity of Dictionary Learning and Other Matrix Factorizations
• Distance Learning in Discriminative Vector Quantization
• Improved Minimax Bounds on the Test and Training Distortion of Empirically Designed Vector Quantizers
• Individual Convergence Rates in Empirical Vector Quantizer Design
• On the Performance of Clustering in Hilbert Spaces
• Nonnegative Matrix Factorization with the Itakura-Saito Divergence: With Application to Music Analysis
• Adaptive Relevance Matrices in Learning Vector Quantization
• Atomic Decomposition by Basis Pursuit
• On the training distortion of vector quantizers
• A local search approximation algorithm for k-means clustering
• NeNMF: An Optimal Gradient Method for Nonnegative Matrix Factorization
• The minimax distortion redundancy in empirical quantizer design
• 10.1162/153244302760200713
• 10.1162/153244303321897690
• Unsupervised Spike Detection and Sorting with Wavelets and Superparamagnetic Clustering
• Rates of convergence in the source coding theorem, in empirical quantizer design, and in universal lossy source coding
• Semidefinite Programming Based Preconditioning for More Robust Near-Separable Nonnegative Matrix Factorization
• $K$-Dimensional Coding Schemes in Hilbert Spaces
• Sparse Coding on the Spot: Spontaneous Retinal Waves Suffice for Orientation Selectivity
• Probability Inequalities for Sums of Bounded Random Variables
• Learning the parts of objects by non-negative matrix factorization
• Manifold Regularized Discriminative Nonnegative Matrix Factorization With Fast Gradient Descent
• Improved Sparse Coding Under the Influence of Perceptual Attention
• A Hebbian/Anti-Hebbian Neural Network for Linear Subspace Learning: A Derivation from Multidimensional Scaling of Streaming Data

This page was built for publication: Dimensionality-Dependent Generalization Bounds for k-Dimensional Coding Schemes