Fundamental limits of symmetric low-rank matrix estimation

DOI10.1007/s00440-018-0845-xzbMath1411.60014arXiv1611.03888OpenAlexW2588219153WikidataQ130001917 ScholiaQ130001917MaRDI QIDQ1740590

Léo Miolane, Marc Lelarge

Publication date: 30 April 2019

Published in: Probability Theory and Related Fields (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1611.03888

Mathematics Subject Classification ID

Random matrices (probabilistic aspects) (60B20) Inference from stochastic processes and spectral analysis (62M15) Random measures (60G57) Statistical aspects of information-theoretic topics (62B10)

Related Items (34)

Fundamental barriers to high-dimensional regression with convex penalties ⋮ The adaptive interpolation method for proving replica formulas. Applications to the Curie–Weiss and Wigner spike models ⋮ Hamilton-Jacobi equations for inference of matrix tensor products ⋮ Strong replica symmetry in high-dimensional optimal Bayesian inference ⋮ Information theoretic limits of learning a sparse rule ⋮ Estimation of low-rank matrices via approximate message passing ⋮ Statistical thresholds for tensor PCA ⋮ Hamilton-Jacobi equations for finite-rank matrix inference ⋮ Statistical limits of spiked tensor models ⋮ A Friendly Tutorial on Mean-Field Spin Glass Techniques for Non-Physicists ⋮ Fundamental limits of detection in the spiked Wigner model ⋮ Testing in high-dimensional spiked models ⋮ Entrywise eigenvector analysis of random matrices with low expected rank ⋮ Mutual information for the sparse stochastic block model ⋮ Statistical inference of finite-rank tensors ⋮ Local laws for multiplication of random matrices ⋮ Local convexity of the TAP free energy and AMP convergence for \(\mathbb{Z}_2\)-synchronization ⋮ Noisy linear inverse problems under convex constraints: exact risk asymptotics in high dimensions ⋮ Universality of regularized regression estimators in high dimensions ⋮ The decimation scheme for symmetric matrix factorization ⋮ Notes on computational-to-statistical gaps: predictions using statistical physics ⋮ TAP free energy, spin glasses and variational inference ⋮ Near-Optimal Bounds for Phase Synchronization ⋮ Phase transition in random tensors with multiple independent spikes ⋮ Charting the replica symmetric phase ⋮ Robust high-dimensional factor models with applications to statistical machine learning ⋮ The adaptive interpolation method: a simple scheme to prove replica formulas in Bayesian inference ⋮ The overlap gap property in principal submatrix recovery ⋮ On the computational tractability of statistical estimation on amenable graphs ⋮ Hamilton-Jacobi equations for mean-field disordered systems ⋮ Phase transition in the spiked random tensor with Rademacher prior ⋮ Hamilton-Jacobi equations for nonsymmetric matrix inference ⋮ Notes on computational hardness of hypothesis testing: predictions using the low-degree likelihood ratio ⋮ A Unifying Tutorial on Approximate Message Passing

Cites Work

• Unnamed Item
• Unnamed Item
• Tightness of the maximum likelihood semidefinite relaxation for angular synchronization
• The eigenvalues and eigenvectors of finite, low rank perturbations of large random matrices
• Exact solution of the gauge symmetric \(p\)-spin glass model on a complete graph
• A generalization of the Lindeberg principle
• Finding one community in a sparse graph
• Information-theoretic thresholds from the cavity method
• Optimality and sub-optimality of PCA. I: Spiked random matrix models
• Broken replica symmetry bounds in the mean field spin glass model
• The largest eigenvalue of rank one deformation of large Wigner matrices
• Phase transition of the largest eigenvalue for nonnull complex sample covariance matrices
• Mutual Information and Minimum Mean-Square Error in Gaussian Channels
• General properties of overlap probability distributions in disordered spin systems. Towards Parisi ultrametricity
• The Nishimori line and Bayesian statistics
• Asymptotic mutual information for the balanced binary stochastic block model
• Information-Theoretic Bounds and Phase Transitions in Clustering, Sparse PCA, and Submatrix Localization
• Statistical Physics of Spin Glasses and Information Processing
• The Sherrington-Kirkpatrick Model
• The Generalized Area Theorem and Some of its Consequences
• Functional Properties of Minimum Mean-Square Error and Mutual Information
• Applications of the Lindeberg Principle in Communications and Statistical Learning
• Tight Bounds on the Capacity of Binary Input Random CDMA Systems
• Envelope Theorems for Arbitrary Choice Sets
• Mean Field Models for Spin Glasses
• Mean Field Models for Spin Glasses

This page was built for publication: Fundamental limits of symmetric low-rank matrix estimation