Statistical learning guarantees for compressive clustering and compressive mixture modeling

DOI10.4171/MSL/21zbMath1478.62165arXiv2004.08085OpenAlexW3159457618MaRDI QIDQ2664825

Gilles Blanchard, Yann Traonmilin, Rémi Gribonval, Nicolas Keriven

Publication date: 18 November 2021

Published in: Mathematical Statistics and Learning (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2004.08085

zbMATH Keywords

clusteringunsupervised learningstatistical learningmixture modelingrandom momentskernel mean embeddingrandom features

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Computational learning theory (68Q32) Compound decision problems in statistical decision theory (62C25)

Related Items

Sketched learning for image denoising, Compressive Learning for Patch-Based Image Denoising, Compressive statistical learning with random feature moments, On strong basins of attractions for non-convex sparse spike estimation: upper and lower bounds

Uses Software

• k-means++
• PhaseLift

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A mathematical introduction to compressive sensing
• Fast rates for empirical vector quantization
• A spectral algorithm for learning mixture models
• Optimal quantizers for Radon random vectors in a Banach space
• Concentration inequalities and model selection. Ecole d'Eté de Probabilités de Saint-Flour XXXIII -- 2003.
• Exact support recovery for sparse spikes deconvolution
• Quantization and clustering with Bregman divergences
• NP-hardness of Euclidean sum-of-squares clustering
• A central limit theorem for k-means clustering
• The empirical characteristic function and its applications
• Stable recovery of low-dimensional cones in Hilbert spaces: one RIP to rule them all
• Quick-means: accelerating inference for K-means by learning fast transforms
• Compressive statistical learning with random feature moments
• On the mathematical foundations of learning
• PhaseLift: Exact and Stable Signal Recovery from Magnitude Measurements via Convex Programming
• Hilbert space embeddings and metrics on probability measures
• Exact Solutions to Super Resolution on Semi-Algebraic Domains in Higher Dimensions
• Compressive Gaussian Mixture Estimation
• Improved Minimax Bounds on the Test and Training Distortion of Empirically Designed Vector Quantizers
• Individual Convergence Rates in Empirical Vector Quantizer Design
• The complexity of the generalized Lloyd - Max problem (Corresp.)
• Quantization and the method of<tex>k</tex>-means
• Refinements of Pinsker's inequality
• The minimax distortion redundancy in empirical quantizer design
• Rates of convergence in the source coding theorem, in empirical quantizer design, and in universal lossy source coding
• Inverse problems in spaces of measures
• Sketching for large-scale learning of mixture models
• Learning Theory