Limit Theorems for Stochastic Gradient Descent in High-Dimensional Single-Layer Networks

Abstract:This paper studies the high-dimensional scaling limits of online stochastic gradient descent (SGD). Building on the work of Ben Arous, Gheissari, and Jagannath on the effective dynamics of SGD, we study the critical scaling regime of the step size for single-layer networks. Below this regime the effective dynamics are governed by deterministic (ballistic) limits, whereas at the critical scale a correction term emerges that changes the phase diagram. Near the fixed points of these dynamics, we show that the diffusive (SDE) limit of the rescaled correlation is an Ornstein-Uhlenbeck process. More precisely, it is mean-reverting whenever the information exponent is at least three. At information exponent two the drift has no universal sign, and the fixed point may become repelling; we show this explicitly for phase retrieval, where the sign is determined by the step size and the noise level. These results illustrate the limitations of deterministic scaling limits in capturing stochastic fluctuations in high-dimensional learning dynamics.

Machine Learning (stat.ML); Machine Learning (cs.LG); Probability (math.PR); Statistics Theory (math.ST)

arXiv:2511.02258 [stat.ML]

(or arXiv:2511.02258v3 [stat.ML] for this version)