Newshot

Bandit Online Submodular Minimisation Using Zeroth-Order Oracles

Summary

arXiv:2611.22130v1 Announce Type: new Abstract: We consider online submodular minimisation under bandit feedback, where at each round a decision maker plays a subset and observes only its cost, while the cost functions, and hence their minimiser, change over time. Existing bandit methods only guarantee static regret, which compares against a single fixed subset and is a weak benchmark when the minimiser moves. This paper provides, to the best of our knowledge, the first method with guarantees for tracking a moving minimiser in this setting. We propose a zeroth-order method built on a two-point oracle for the Lov\'asz extension whose two evaluations are both subsets that can be played. The perturbed and base points are rounded by a common random threshold, and drawing the smoothing direction from the unit sphere makes the base evaluation a zero-mean control variate, so the oracle is an unbiased estimator of the smoothed gradient. We establish dynamic regret bounds of order $O\big((1+\sq…

Original text(via arXiv stat.ML)

Statistics > Machine Learning

Title:Bandit Online Submodular Minimisation Using Zeroth-Order Oracles

Abstract:We consider online submodular minimisation under bandit feedback, where at each round a decision maker plays a subset and observes only its cost, while the cost functions, and hence their minimiser, change over time. Existing bandit methods only guarantee static regret, which compares against a single fixed subset and is a weak benchmark when the minimiser moves. This paper provides, to the best of our knowledge, the first method with guarantees for tracking a moving minimiser in this setting. We propose a zeroth-order method built on a two-point oracle for the Lovász extension whose two evaluations are both subsets that can be played. The perturbed and base points are rounded by a common random threshold, and drawing the smoothing direction from the unit sphere makes the base evaluation a zero-mean control variate, so the oracle is an unbiased estimator of the smoothed gradient. We establish dynamic regret bounds of order $O\big((1+\sqrt{P^\ast_N})N^{3/4}\big)$ in general and $O\big((1+\sqrt{P^\ast_N})N^{2/3}\big)$ under a sufficiently small drift, where $P^\ast_N$ is the path length of the minimiser sequence, together with the corresponding $O(N^{3/4})$ and $O(N^{2/3})$ static regret bounds. Numerically, the method attains lower regret than the algorithm of (Hazan and Kale (2012)), with the advantage growing with the path length.
Subjects:Machine Learning (stat.ML) ; Machine Learning (cs.LG)
Cite as:arXiv:2611.22130 [stat.ML]
(or arXiv:2611.22130v1 [stat.ML] for this version)
https://doi.org/10.48550/arXiv.2611.22130 arXiv-issued DOI via DataCite (pending registration)

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 stat.ML
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 ↗