Applications of the Lindeberg Principle in Communications and Statistical Learning

DOI10.1109/TIT.2011.2112231MaRDI QIDQ5281002zbMATH OpenFDO

Authors

Publication date 27 July 2017

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

Full work available at URL https://doi.org/10.1109/TIT.2011.2112231

Mathematics Subject Classification ID

Random matrices (probabilistic aspects) (60B20) Central limit and other weak theorems (60F05) Ridge regression; shrinkage estimators (Lasso) (62J07) Communication theory (94A05)

Cited in

(16)

• Fundamental limits of symmetric low-rank matrix estimation
• Fundamental barriers to high-dimensional regression with convex penalties
• Approximation to stochastic variance reduced gradient Langevin dynamics by stochastic delay differential equations
• Comparison theorem for some extremal eigenvalue statistics
• Approximation to stable law by the Lindeberg principle
• High dimensional robust M-estimation: asymptotic variance via approximate message passing
• Asymptotic mutual information for the balanced binary stochastic block model
• Random-link matching problems on random regular graphs
• A probability approximation framework: Markov process approach
• Universality of approximate message passing with semirandom matrices
• Universality of regularized regression estimators in high dimensions
• Entrywise dynamics and universality of general first order methods
• Normal approximation for call function by refined Lindeberg principle
• Universality laws for Gaussian mixtures in generalized linear models
• Differentially private learning beyond the classical dimensionality regime
• Universality of estimators for high-dimensional linear models with block dependency

This page was built for publication: Applications of the Lindeberg Principle in Communications and Statistical Learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5281002)