Saved in:
Bibliographic Details
Main Authors: Flamand, Kessang, Brunel, Victor-Emmanuel
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.15538
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • We study the asymptotic shape of the trajectory of the stochastic gradient descent algorithm applied to a convex objective function. Under mild regularity assumptions, we prove a functional central limit theorem for the properly rescaled trajectory. Our result characterizes the long-term fluctuations of the algorithm around the minimizer by providing a diffusion limit for the trajectory. In contrast with classical central limit theorems for the last iterate or Polyak-Ruppert averages, this functional result captures the temporal structure of the fluctuations and applies to non-smooth settings such as robust location estimation, including the geometric median.