DeepAI AI Chat
Log In Sign Up

High-dimensional inference: a statistical mechanics perspective

by   Jean Barbier, et al.

Statistical inference is the science of drawing conclusions about some system from data. In modern signal processing and machine learning, inference is done in very high dimension: very many unknown characteristics about the system have to be deduced from a lot of high-dimensional noisy data. This "high-dimensional regime" is reminiscent of statistical mechanics, which aims at describing the macroscopic behavior of a complex system based on the knowledge of its microscopic interactions. It is by now clear that there are many connections between inference and statistical physics. This article aims at emphasizing some of the deep links connecting these apparently separated disciplines through the description of paradigmatic models of high-dimensional inference in the language of statistical mechanics. This article has been published in the issue on artificial intelligence of Ithaca, an Italian popularization-of-science journal. The selected topics and references are highly biased and not intended to be exhaustive in any ways. Its purpose is to serve as introduction to statistical mechanics of inference through a very specific angle that corresponds to my own tastes and limited knowledge.


page 1

page 2

page 3

page 4


Statistical inference as Green's functions

Statistical inference from data is foundational task in science. Recentl...

High dimensional statistical inference: theoretical development to data analytics

This article is due to appear in the Handbook of Statistics, Vol. 43, El...

Statistical Mechanics of High-Dimensional Inference

To model modern large-scale datasets, we need efficient algorithms to in...

Quantifying Relevance in Learning and Inference

Learning is a distinctive feature of intelligent behaviour. High-through...

Pattern Discovery and Computational Mechanics

Computational mechanics is a method for discovering, describing and quan...

Statistical Inference in High-Dimensional Generalized Linear Models with Asymmetric Link Functions

We have developed a statistical inference method applicable to a broad r...

Understanding Phase Transitions via Mutual Information and MMSE

The ability to understand and solve high-dimensional inference problems ...