Positive Semi-definite Embedding for Dimensionality Reduction and Out-of-Sample Extensions

DOI10.1137/20M1370653OpenAlexW4300643008MaRDI QIDQ5065468

Michaël Fanuel, Antoine Aspeel, Jean-Charles Delvenne, Johan A. K. Suykens

Publication date: 21 March 2022

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

Full work available at URL: https://arxiv.org/abs/1711.07271

zbMATH Keywords

kernel methodsdimensionality reductiondiffusion mapssemi-definite program

Mathematics Subject Classification ID

Statistics (62-XX) Semidefinite programming (90C22) Function spaces arising in harmonic analysis (42B35) Linear operator approximation theory (47A58) Kernel functions in one complex variable and applications (30C40) Applications of operator theory in probability theory and statistics (47N30)

Related Items

Unnamed Item

Uses Software

• SDPLR
• t-SNE
• UMAP

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Mercer's theorem on general domains: on the interaction between measures, kernels, and RKHSs
• Virtual continuity of measurable functions of several variables and embedding theorems
• Tightness of the maximum likelihood semidefinite relaxation for angular synchronization
• A nonlinear programming algorithm for solving semidefinite programs via low-rank factorization
• Diffusion maps
• Geometric harmonics: a novel tool for multiscale out-of-sample extension of empirical functions
• Integration of virtually continuous functions over bistochastic measures and the trace formula for nuclear operators
• Nonconvex Phase Synchronization
• Error bounds for learning the kernel
• Phase transitions in semidefinite relaxations
• Kernels of Trace Class Operators
• Geometric diffusions as a tool for harmonic analysis and structure definition of data: Diffusion maps
• Scalable Semidefinite Programming
• Scattered Data Approximation