No article text was recorded for this version.
Gaussian equivalence principle
Version 1 of 198 papers137 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Universality of empirical risk minimization
- Blog: Universality Laws for High-Dimensional Learning with Random Features
- Blog: Random Matrix Theory Proves that Deep Learning Representations of GAN-data Behave as Gaussian Mixtures
- Blog: Learning Gaussian Mixtures with Generalised Linear Models: Precise Asymptotics in High-dimensions
- Blog: Dyson Equation for Correlated Linearizations and Test Error of Random Features Regression
- Blog: Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentatio
- Blog: Anisotropic local law for non-separable sample covariance matrices
- Blog: Universality laws for Gaussian mixtures in generalized linear models
- Blog: On the Inherent Regularization Effects of Noise Injection During Training
- Blog: Asymptotics of feature learning in two-layer networks after one gradient-step
- Blog: Universality laws for Gaussian mixtures in generalized linear models
- Blog: Asymptotics of Linear Regression with Linearly Dependent Data
- Blog: Universality of max-margin classifiers
- Blog: Universality laws for Gaussian mixtures in generalized linear models*
- Blog: Gaussian Universality for Diffusion Models
- Blog: The Unexpected Deterministic and Universal Behavior of Large Softmax Classifiers
- Blog: Learning curves of generic features maps for realistic datasets with a teacher-student model
- Blog: Random Matrix Theory Proves that Deep Learning Representations of GAN-data Behave as Gaussian Mixtures
- Blog: Deterministic equivalent and error universality of deep random features learning
- Blog: Fundamental Limits of Matrix Sensing: Exact Asymptotics, Universality, and Applications
- Blog: A Random Matrix Perspective on Mixtures of Nonlinearities in High Dimensions
- Blog: Universality of empirical risk minimization
- Blog: The generalization error of max-margin linear classifiers: Benign overfitting and high dimensional asymptotics in the overparametrized regime
- Blog: On the Spectrum of Random Features Maps of High Dimensional Data
- Blog: Learning curves of generic features maps for realistic datasets with a teacher-student model*
- Blog: Exact threshold for approximate ellipsoid fitting of random points
- Blog: Learning Hierarchical Polynomials of Multiple Nonlinear Features
- Blog: Are Gaussian Data All You Need? The Extents and Limits of Universality in High-Dimensional Generalized Linear Estimation
- Blog: Sharp Asymptotics of Kernel Ridge Regression Beyond the Linear Regime
- Blog: On the Inherent Regularization Effects of Noise Injection During Training
- Blog: Learning Gaussian Mixtures with Generalized Linear Models: Precise Asymptotics in High-dimensions
- Blog: Gaussian Universality of Linear Classifiers with Random Labels in High-Dimension
- Blog: The Gaussian equivalence of generative models for learning with two-layer neural networks
- Blog: The Gaussian equivalence of generative models for learning with shallow neural networks
- Blog: Universality in Transfer Learning for Linear Models
- Blog: A statistical mechanics framework for Bayesian deep neural networks beyond the infinite-width limit
- Blog: Deep Equilibrium Models are Almost Equivalent to Not-so-deep Explicit Models for High-dimensional Gaussian Mixtures
- Blog: Fundamental Limits of Non-Linear Low-Rank Matrix Estimation
- Blog: Gaussian Equivalence for Self-Attention: Asymptotic Spectral Analysis of Attention Matrix
- Blog: Asymptotics of Random Feature Regression Beyond the Linear Scaling Regime
- Blog: Capturing the learning curves of generic features maps for realistic data sets with a teacher-student model
- Blog: Spin glass theory and its new challenge: structured disorder
- Blog: Information limits and Thouless-Anderson-Palmer equations for spiked matrix models with structured noise
- Blog: Local minima of the empirical risk in high dimension: General theorems and convex examples
- Blog: On the Consistency of Feature Selection With Lasso for Non-linear Targets
- Blog: A Comprehensive Analysis on the Learning Curve in Kernel Ridge Regression
- Blog: Deterministic equivalent and error universality of deep random features learning
- Blog: Precise Asymptotic Analysis of Deep Random Feature Models
- Blog: Neural Population Geometry and Optimal Coding of Tasks with Shared Latent Structure
- Blog: Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks
- Blog: A Precise Performance Analysis of Learning with Random Features
- Blog: Dynamics of Temporal Difference Reinforcement Learning
- Blog: A Comprehensive Analysis on the Learning Curve in Kernel Ridge\n Regression
- Blog: Kernel regression in high dimensions: Refined analysis beyond double descent
- Blog: More is Better: when Infinite Overparameterization is Optimal and Overfitting is Obligatory
- Blog: Bayes-optimal Learning of Deep Random Networks of Extensive-width
- Blog: Predicting Kernel Regression Learning Curves from Only Raw Data Statistics
- Blog: Demystifying Disagreement-on-the-Line in High Dimensions
- Blog: Universality in Transfer Learning for Linear Models
- Blog: Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks
Showing 60 of 98 papers.
History & citation
Current · Permanent link
- The Gaussian Equivalence Principle in High Dimensions merged into this direction (72% overlap)
- Gaussian Universality in High Dimensional Learning merged into this direction (81% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_gaussian_equivalence_principle_3ead51a2,
title = {Gaussian equivalence principle},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/gaussian-equivalence-principle/rdr_3ead51a27493479685f6e11dd9e2eb87},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_gaussian_equivalence_principle_3ead51a2_v1,
title = {Gaussian equivalence principle},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/gaussian-equivalence-principle/rdr_3ead51a27493479685f6e11dd9e2eb87/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}