High-dimensional learning dynamics of multi-pass Stochastic Gradient Descent in multi-index models

arXiv:2601.21093 · stat.ML, cs.LG, math.OC, math.PR, math.ST, stat.TH · Submitted 2026-01-28 · Read on arXiv

stat.ML, cs.LG, math.OC, math.PR, math.ST, stat.TH

Submitted: 2026-01-28

Updated: 2026-10-21

Terminology

• Gradient Flow — 2× in this paper · explained in 2 episodes
• Stochastic Gradient Descent — 2× in this paper
• Stochastic Gradient Descent (SGD) — 1× in this paper · explained in 5 episodes
• Stochastic Modified Equation — 1× in this paper

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• Scalable Posterior Uncertainty for Flexible Density-Based Clustering
• Efficient quadratic entropy with distance sketches
• Embedding-Bias in Conditional Independence Testing