activity
20232026
most citedUniversality of max-margin classifiers

2 citations · 2 across the 4 of their papers we have counts for

collaborators

8 papers

cs.LG2026

Replica Symmetry Breaking and Algorithmic Thresholds in Empirical Risk Minimization under Multi-Index Model

Andrea Montanari, Kangjie Zhou

Modern machine learning models are trained by optimizing high-dimensional non-convex empirical risk functions. Such cost functions can have a multitude of local optima and yet, gra…

math.ST2026

Topological trivialization in non-convex empirical risk minimization

Andrea Montanari, Basil Saeed

Given data , with standard -dimensional Gaussian feature vectors, and response variables, we study t…

stat.ML2025

Dynamical Decoupling of Generalization and Overfitting in Large Two-Layer Networks

Andrea Montanari, Pierfrancesco Urbani

Understanding the inductive bias and generalization properties of large overparametrized machine learning models requires to characterize the dynamics of the training algorithm. We…

stat.ML2025

Local minima of the empirical risk in high dimension: General theorems and convex examples

Kiana Asgari, Andrea Montanari, Basil Saeed

We consider a general model for high-dimensional empirical risk minimization whereby the data are -dimensional Gaussian vectors, the model is parametrized by $\ma…

cs.CV2024

Scaling Training Data with Lossy Image Compression

Katherine L. Mentzer, Andrea Montanari

Empirically-determined scaling laws have been broadly successful in predicting the evolution of large machine learning models with training data and number of parameters. As a cons…

math.PR2024

Which exceptional low-dimensional projections of a Gaussian point cloud can be found in polynomial time?

Andrea Montanari, Kangjie Zhou

Given -dimensional standard Gaussian vectors , we consider the set of all empirical distributions of its -dimensional projections, f…