Non-Negative Principal Component Analysis: Message Passing Algorithms and Sharp Asymptotics

DOI10.1109/TIT.2015.2457942zbMath1359.62224arXiv1406.4775OpenAlexW1625271478MaRDI QIDQ2976981

Emile Richard, Andrea Montanari

Publication date: 28 April 2017

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

Full work available at URL: https://arxiv.org/abs/1406.4775

Mathematics Subject Classification ID

Factor analysis and principal components; correspondence analysis (62H25) Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Related Items (30)

Approximate message passing algorithms for rotationally invariant matrices ⋮ Statistical physics and representations in real and artificial neural networks ⋮ Unnamed Item ⋮ Estimation of low-rank matrices via approximate message passing ⋮ Statistical limits of spiked tensor models ⋮ Riemannian optimization via Frank-Wolfe methods ⋮ Generalized TAP Free Energy ⋮ Sion’s Minimax Theorem in Geodesic Metric Spaces and a Riemannian Extragradient Algorithm ⋮ Fundamental limits of weak recovery with applications to phase retrieval ⋮ A semismooth Newton based augmented Lagrangian method for nonsmooth optimization on matrix manifolds ⋮ Approximate message passing for sparse matrices with application to the equilibria of large ecological Lotka-Volterra systems ⋮ Unnamed Item ⋮ Singular value problems under nonnegativity constraints ⋮ Local convexity of the TAP free energy and AMP convergence for \(\mathbb{Z}_2\)-synchronization ⋮ On the TAP equations via the cavity approach in the generic mixed \(p\)-spin models ⋮ Unnamed Item ⋮ A brief introduction to manifold optimization ⋮ Notes on computational-to-statistical gaps: predictions using statistical physics ⋮ Phase transition in random tensors with multiple independent spikes ⋮ Simple algorithms for optimization on Riemannian manifolds with constraints ⋮ Sparse equisigned PCA: algorithms and performance bounds in the noisy rank-1 setting ⋮ Optimality and sub-optimality of PCA. I: Spiked random matrix models ⋮ Universality of approximate message passing algorithms ⋮ The distribution of the Lasso: uniform control over sparse balls and adaptive parameter tuning ⋮ Nonconvex Phase Synchronization ⋮ Random matrix theory and its applications ⋮ Phase transition in the spiked random tensor with Rademacher prior ⋮ A Unifying Tutorial on Approximate Message Passing ⋮ Stochastic Difference-of-Convex-Functions Algorithms for Nonconvex Programming ⋮ Optimal low-degree hardness of maximum independent set

This page was built for publication: Non-Negative Principal Component Analysis: Message Passing Algorithms and Sharp Asymptotics