On the training distortion of vector quantizers

DOI10.1109/18.850705MaRDI QIDQ4545788zbMATH OpenOpenAlexFDO

Authors Tamás Linder

Publication date 15 August 2002

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://semanticscholar.org/paper/72b339d8b2aa3f030a27b731c837cdebe0223a01

zbMATH Keywords

source codingtraining distortionvector quantizer

Mathematics Subject Classification ID

Source coding (94A29)

Recommendations

• Upper bounds on empirically optimal quantizers
• Learning Theory
• Improved Minimax Bounds on the Test and Training Distortion of Empirically Designed Vector Quantizers
• The minimax distortion redundancy in empirical quantizer design
• Distortion bounds for vector quantizers with finite codebook size

Cited in

(11)

• Redesigning vector quantizers using implicitly estimated probability density functions
• A notion of stability for k-means clustering
• On Hölder fields clustering
• Improved Minimax Bounds on the Test and Training Distortion of Empirically Designed Vector Quantizers
• Upper bounds on empirically optimal quantizers
• Distortion bounds for vector quantizers with finite codebook size
• Dimensionality-dependent generalization bounds for \(k\)-dimensional coding schemes
• Learning Theory
• On the number of groups in clustering
• Asymptotic theory of geometric and adaptive k-means clustering
• A penalized criterion for selecting the number of clusters for K-medians

This page was built for publication: On the training distortion of vector quantizers

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4545788)