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