On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

8 results for “CGMT”

Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentationmath.ST

Paper generalizes Gaussian universality and CGMT to dependent data, impacting data augmentation in high-dimensional logistic regression.

problem Limitation of Gaussian universality and CGMT in handling dependent data.

method Generalizes Gaussian universality and CGMT to dependent data (block dependence, m-dependence, mixing). Establishes a novel CGMT framework.

result Gaussian universality holds for high-dimensional logistic regression under various types of dependence.

logistic regression dependence Gaussian universality CGMT data augmentation

2025-02-10abs ↗pdf ↗

A Novel Gaussian Min-Max Theorem and its Applicationscs.LG

New Gaussian min-max theorem extends classical results to non-i.i.d. Gaussian matrices.

problem Extending classical Gaussian min-max theorems to non-i.i.d. Gaussian matrices.

method Identifying a new pair of Gaussian processes that satisfy comparison inequalities.

result New Gaussian min-max and convex Gaussian min-max theorems with applications in multi-source Gaussian regression and binary classification.

Gaussian processes min-max theorem non-i.i.d. Gaussian matrices multi-source Gaussian regression binary classification

2024-02-12abs ↗pdf ↗

Precise Performance of Linear Denoisers in the Proportional Regimestat.ML

New linear denoiser outperforms standard Wiener filter in noisy data.

problem Improving denoising performance for unknown covariance data.

method Synthetically constructed noisy samples to train a linear denoiser using least-squares approximation.

result Optimal denoiser found using the Convex Gaussian Min-Max Theorem (CGMT) for proportional regime.

denoising linear filter Wiener filter proportional regime CGMT

2026-03-19abs ↗pdf ↗

A Model of Double Descent for High-dimensional Binary Linear Classificationstat.ML

Model reveals double descent in binary linear classification.

problem Investigating classification error in high-dimensional binary linear classification.

method Gradient descent on logistic loss, maximum-likelihood, max-margin (SVM) solutions, and convex Gaussian min-max theorem.

result Double descent phenomenon observed in classification error for varying overparameterization ratio.

double descent binary classification gradient descent logistic regression overparameterization

2019-11-13abs ↗pdf ↗

Random Features Model with General Convex Regularization: A Fine Grained Analysis with Precise Asymptotic Learning Curvesstat.ML

We analyze learning curves of RF models with convex regularization and derive precise asymptotic expressions.

problem Understanding the learning curves of RF models with general convex regularization.

method Novel multi-level application of the convex Gaussian min max theorem (CGMT) to compute precise asymptotic expressions.

result Precise asymptotic expressions for learning curves of RF models with separable strongly convex regularization or

\ell_1

regularization.

Random Features Convex Regularization Learning Curves Asymptotic Analysis Convex Gaussian Min Max Theorem

2022-04-06abs ↗pdf ↗

Characterization of Gaussian Universality Breakdown in High-Dimensional Empirical Risk Minimizationstat.ML

The study uncovers the breakdown of Gaussian universality in high-dimensional empirical risk minimization.

problem Understanding the breakdown of Gaussian universality in high-dimensional empirical risk minimization.

method Extending the Convex Gaussian Min-Max Theorem to non-Gaussian settings, deriving asymptotic min-max characterizations, and proving asymptotic equivalence of regularizers.

result The projection of the ERM estimator onto a test covariate approximately follows a Gaussian convolution under certain conditions.

Empirical Risk Minimization Gaussian Universality High-Dimensional Statistics Convex Min-Max Theorem Non-Gaussian Data

2026-04-03abs ↗pdf ↗

Anonymous Learning via Look-Alike Clustering: A Precise Analysis of Model Generalizationcs.LG

The paper analyzes how clustering sensitive data can improve model generalization without revealing individual information.

problem Ensuring user data privacy in personalized recommendation systems.

method Look-alike clustering to replace sensitive features with cluster averages, analyzed using Convex Gaussian Minimax Theorem.

result Training models using anonymous cluster centers can improve generalization error, especially in high-dimensional settings.

look-alike clustering model generalization privacy-preserving machine learning asymptotic analysis Convex Gaussian Minimax Theorem

2023-10-06abs ↗pdf ↗

Regularized Variational and Spectral Log-Density-Ratio Estimation in the Gaussian Location Modelcs.LG

Estimates Gaussian location model with ridge regularization, comparing variational and spectral methods.

problem Estimating parameters in Gaussian location model with regularization.

method Ridge-regularized log-density-ratio estimation, variational and spectral approaches.

result Regularized variational estimator has lower risk with many observations, spectral estimator with fewer observations.

Gaussian location model ridge regularization log-density-ratio variational estimation spectral estimation

2026-07-02abs ↗pdf ↗