High-dimensional rank-one nonsymmetric matrix decomposition: the spherical case

Abstract

We consider the problem of estimating a rank-one nonsymmetric matrix under additive white Gaussian noise. The matrix to estimate can be written as the outer product of two vectors and we look at the special case in which both vectors are uniformly distributed on spheres. We prove a replica-symmetric formula for the average mutual information between these vectors and the observations in the high-dimensional regime. This goes beyond previous results which considered vectors with independent and identically distributed elements. The method used can be extended to rank-one tensor problems.

arXiv commentWill appear in 2020 IEEE International Symposium on Information Theory (ISIT). Long version with appendices, 26 pages

References in corpus (10)

• Tensor Decomposition for Signal Processing and Machine Learning
• Tensor Decompositions for Signal Processing Applications From Two-way to Multiway Component Analysis
• Broken Replica Symmetry Bounds in the Mean Field Spin Glass Model
• The Thermodynamic Limit in Mean Field Spin Glass Models
• Optimal Errors and Phase Transitions in High-Dimensional Generalized Linear Models
• The largest eigenvalue of rank one deformation of large Wigner matrices
• Constrained Low-rank Matrix Estimation: Phase Transitions, Approximate Message Passing and Applications
• The adaptive interpolation method for proving replica formulas. Applications to the Curie-Weiss and Wigner spike models
• High-dimensional rank-one nonsymmetric matrix decomposition: the spherical case
• Legendre Duality of Spherical and Gaussian Spin Glasses

Cited by in corpus (3)

• An inference problem in a mismatched setting: a spin-glass model with Mattis interaction
• High-dimensional rank-one nonsymmetric matrix decomposition: the spherical case
• On the free energy of vector spin glasses with non-convex interactions