Applications of Lindeberg Principle in Communications and Statistical\n Learning

2010/04/04 by Satish Babu Korada, Andrea Montanari, Korada, Satish Babu +1 · 1 citation
Mathematics · Computer Science · #Random Matrices and Applications #Graph theory and applications #Matrix Theory and Algorithms

paper · pdf · doi:10.48550/arxiv.1004.0557

Abstract

We use a generalization of the Lindeberg principle developed by Sourav\nChatterjee to prove universality properties for various problems in\ncommunications, statistical learning and random matrix theory. We also show\nthat these systems can be viewed as the limiting case of a properly defined\nsparse system. The latter result is useful when the sparse systems are easier\nto analyze than their dense counterparts. The list of problems we consider is\nby no means exhaustive. We believe that the ideas can be used in many other\nproblems relevant for information theory.\n

Citations

• Atomic Decomposition by Basis Pursuit

Cited by

• Statistical Limits for Finite-Rank Tensor Estimation

Related

• Universality Laws for High-Dimensional Learning with Random Features
• On Universal Features for High-Dimensional Learning and Inference
• Universality of the Distribution Functions of Random Matrix Theory. II
• Four lectures on probabilistic methods for data science
• Randomness Conservation Inequalities; Information and Independence in Mathematical Theories