跳到正文
arXiv cs.AI· Lisha Chen·· 56 分钟前AI 评分34

ChatGPT 5.4 Thinking 协助证明:随机多梯度下降 SMG 收敛率的改进填平空隙

Improved Convergence Rates for Stochastic Multi-Gradient Descent which Close the Gap: A Proof by AI

AI 导读

一篇 arXiv 预_print 证明,在光滑非凸随机多目标优化中,随机多梯度下降(SMG)在常数步长和线性增长的 mini-batch 下,输出处的期望平方 Pareto-平稳性度量达 $\tilde{O}(T^{-1})$,改进了 Chen et al.(JMLR, 2024)的 $\tilde{O}(T^{-1/4})$ 界且不需有界梯度。

正文 · 原文

View PDF HTML (experimental)

Abstract:For smooth nonconvex stochastic multi-objective optimization, stochastic multi-gradient descent (SMG) computes an approximate steepest common descent direction of the objectives from stochastic gradients. Under standard assumptions, this note establishes a new convergence rate for SMG in terms of the squared Pareto-stationarity (PS) measure. With a constant stepsize and linearly growing mini-batches, the expected squared empirical PS measure at the algorithm's output is $\tilde{O}(T^{-1})$ after $T$ iterations. This improves on the $\tilde{O}(T^{-1/4})$ bound obtained by Chen et al. (JMLR, 2024) for linearly growing batches, without requiring bounded gradients. Here, $\tilde{O}(\cdot)$ suppresses logarithmic factors. The key to the rate improvement is to exploit the Lipschitz continuity of the PS measure, defined by the norm of the multi-gradient descent algorithm (MGDA) direction, rather than the $(1/2)$-Hölder continuity of the MGDA direction used by Chen et al. (2024). For variants of MoCo and MoCo+ with exact MGDA updates and constant batch sizes, the analysis gives expected squared empirical PS rates of $O(T^{-1/2})$ and $\tilde{O}(T^{-2/3})$, respectively. These bounds match the corresponding single-objective momentum rates up to logarithmic factors. The proof was accidentally discovered while the author was preparing homework for a graduate course: ChatGPT 5.4 Thinking Extended generated the initial proof strategy for the main SMG result in response to an author-written homework-solution prompt; the author then verified and reorganized the resulting argument. The appendices document the prompt, summarize the student submissions with LLM disclosures, and present additional proofs and results on momentum-based stochastic MGDA.
Comments: 20 pages, preprint, add results and proofs for momentum-based methods, improve the literature discussion
Subjects: Optimization and Control (math.OC); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
MSC classes: 90C29 (Primary), 90C15, 90C26, 90C30 (Secondary)
Cite as: arXiv:2607.18174 [math.OC]
  (or arXiv:2607.18174v2 [math.OC] for this version)
  https://doi.org/10.48550/arXiv.2607.18174

arXiv-issued DOI via DataCite

Submission history

From: Lisha Chen [view email]
[v1] Mon, 20 Jul 2026 17:13:07 UTC (42 KB)
[v2] Sun, 6 Sep 2026 23:37:52 UTC (30 KB)

来源:arXiv cs.AI · arxiv.org