---
title: "Exact Theory and Optimal Stepsizes for Stochastic Gradient Descent in Smooth Convex Minimization"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2610.42048v1"
permalink: "https://feed.astralor.com/items/itm_4a973854ab72b01676a5b2a7"
published: "2026-10-30T17:14:59.000Z"
score: 52
channel: "ai"
tags: ["Exact Theory","Optimal Stepsizes","Stochastic Gradient Descent","Smooth Convex Minimization","Throughout","Among"]
---

# Exact Theory and Optimal Stepsizes for Stochastic Gradient Descent in Smooth Convex Minimization

## 速览

This work considers the design of stepsize schedules for stochastic gradient descent in smooth convex optimization. Throughout, we assume that gradient noise is conditionally zero-mean with bounded variance. Among probl…

## 关键点

- This work considers the design of stepsize schedules for stochastic gradient descent in smooth convex optimization.
- Throughout, we assume that gradient noise is conditionally zero-mean with bounded variance.
- Among problems with dimension $d\geq N+1$, we provide an exact worst-case analysis of the expected suboptimality of stochastic gradient descent's final iterate.

## 全文

This work considers the design of stepsize schedules for stochastic gradient descent in smooth convex optimization. Throughout, we assume that gradient noise is conditionally zero-mean with bounded variance. Among problems with dimension $d\geq N+1$, we provide an exact worst-case analysis of the expected suboptimality of stochastic gradient descent's final iterate. Our analysis applies to any (potentially nonconstant) schedule of $N$ stepsizes in $[0,1.5]^N$. Here, exact means that we provide a matching objective function and noise distributions where our guarantee is attained. Whenever the variance bound is at least $Ω(1/\sqrt{N})$, our theory provides the minimax optimal stepsize schedule for stochastic gradient descent and proves its uniqueness. These optimal stepsizes monotonically decrease, ruling out any accelerations in expected final suboptimality from fixed fractal schedules observed in the deterministic case.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_4a973854ab72b01676a5b2a7