A Novel Gaussian Min–Max Theorem and Its Applications
- 4 August 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Theory
- Vol. 71 (11) , 8777-8797
Abstract
A celebrated result by Gordon allows one to compare the min-max behavior of two Gaussian processes if certain inequality conditions are met. The consequences of this result include the Gaussian min-max (GMT) and convex Gaussian min-max (CGMT) theorems which have had far-reaching implications in high-dimensional statistics, machine learning, non-smooth optimization, and signal processing. Both theorems rely on a pair of Gaussian processes, first identified by Slepian, that satisfy Gordon’s comparison inequalities. In this paper, we identify a new pair of Gaussian processes satisfying these inequalities. The resulting theorems extend the classical GMT and CGMT Theorems from the case where the underlying Gaussian matrix in the primary process has iid rows to where it has independent but non-identically-distributed ones. The new CGMT is applied to the problems of multi-source Gaussian regression, as well as to binary classification of general Gaussian mixture models.Keywords
All Related Versions
This publication has 9 references indexed in Scilit:
- The generalization error of max-margin linear classifiers: Benign overfitting and high dimensional asymptotics in the overparametrized regimeThe Annals of Statistics, 2025
- Regularized Linear Regression for Binary Classification2024
- Precise statistical analysis of classification accuracies for adversarial trainingThe Annals of Statistics, 2022
- Precise Error Analysis of Regularized $M$ -Estimators in High DimensionsIEEE Transactions on Information Theory, 2018
- A rewriting system for convex optimization problemsJournal of Control and Decision, 2017
- Concentration Inequalities2013
- On Milman's inequality and random subspaces which escape through a mesh in ℝ n1988
- Some inequalities for Gaussian processes and applicationsIsrael Journal of Mathematics, 1985
- The One-Sided Barrier Problem for Gaussian NoiseBell System Technical Journal, 1962