Improved linear embeddings via Lagrange duality

DOI10.1007/S10994-018-5729-XzbMath1482.62069arXiv1711.11527OpenAlexW2963359013MaRDI QIDQ669310

Juan-Miguel Gracia

Publication date: 15 March 2019

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1711.11527

zbMATH Keywords

convex relaxationdimensionality reductionconvex and non-convex optimizationnear isometric embeddings

Mathematics Subject Classification ID

Factor analysis and principal components; correspondence analysis (62H25) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Nonconvex programming, global optimization (90C26) Optimality conditions and duality in mathematical programming (90C46) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20)

Uses Software

• MNIST

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Problems and results in extremal combinatorics. I.
• Optimal Bounds for Johnson-Lindenstrauss Transforms and Streaming Problems with Subconstant Error
• Extensions of Lipschitz mappings into a Hilbert space
• Approximate clustering via core-sets
• NuMax: A Convex Approach for Learning Near-Isometric Linear Embeddings

This page was built for publication: Improved linear embeddings via Lagrange duality