cs.LGJun 26, 2026

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

Authors: Andrea MontanariKangjie Zhou

Organizations: Department of Mathematics and Department of Statistics, Stanford University · Department of Statistics, Columbia University

Abstract

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, gradient-based optimization appears to converge to near-global optima. Within a simple supervised learning setting, we develop a precise picture of which parts of the empirical risk landscape are accessible by polynomial-time algorithms. We are given i.i.d. pairs {(xi,yi):  1in}\{(\boldsymbol{x}_i,y_i):\; 1 \le i\le n\} with xiRd\boldsymbol{x}_i\in \mathbb{R}^d standard Gaussian feature vectors, and yiRy_i\in\mathbb{R} response variables that depend on xi\boldsymbol{x}_i through their projections on an unknown kk-dimensional subspace. We use empirical risk minimization to learn a model that depends on an mm-dimensional projection of the data (e.g., an mm-neurons neural network). We propose an incremental approximate message passing (IAMP) algorithm and precisely characterize the training error it achieves, as well as the relation between test and training error, in the high dimensional asymptotics n,dn,d\to\infty, with n/dα(0,+)n/d\toα\in (0, +\infty). Based on earlier work in related models, we expect that the performance achieved by our algorithm is optimal among polynomial-time algorithms.

Explore similar work

CardsList
  1. Learning Multi-Index Models with Hyper-Kernel Ridge Regression

    Oct 2, 2025Shuo Huang, Hippolyte Labarrière, Ernesto De Vito +2Kernel Ridge RegressionDeep Network