Newshot

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

Summary

arXiv:2607.18174v2 Announce Type: cross 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 $(1/2)$-H\"older continuity of the MGDA…

Original text(via arXiv cs.AI)

Mathematics > Optimization and Control

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

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

Access Paper:

  • HTML (experimental)

Current browse context:

References & Citations

  • Google Scholar
  • Semantic Scholar

BibTeX formatted citation

Bookmark

Bibliographic and Citation Tools

Code, Data and Media Associated with this Article

Demos

Recommenders and Search Tools

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

The text above was extracted automatically from the source page and may miss images, tables or code blocks. The original is authoritative.

Published by arXiv cs.AI
This site only summarises and aggregates; copyright stays with the original author. Headlines and summaries follow the source — where they differ, the original wins.
Read the original ↗