Computer Science > Machine Learning
[Submitted on 14 Nov 2022 (v1), last revised 18 Oct 2024 (this version, v7)]
Title:Contextual Bandits with Packing and Covering Constraints: A Modular Lagrangian Approach via Regression
View PDF HTML (experimental)Abstract:We consider contextual bandits with linear constraints (CBwLC), a variant of contextual bandits in which the algorithm consumes multiple resources subject to linear constraints on total consumption. This problem generalizes contextual bandits with knapsacks (CBwK), allowing for packing and covering constraints, as well as positive and negative resource consumption. We provide the first algorithm for CBwLC (or CBwK) that is based on regression oracles. The algorithm is simple, computationally efficient, and statistically optimal under mild assumptions. Further, we provide the first vanishing-regret guarantees for CBwLC (or CBwK) that extend beyond the stochastic environment. We side-step strong impossibility results from prior work by identifying a weaker (and, arguably, fairer) benchmark to compare against. Our algorithm builds on LagrangeBwK (Immorlica et al., FOCS 2019), a Lagrangian-based technique for CBwK, and SquareCB (Foster and Rakhlin, ICML 2020), a regression-based technique for contextual bandits. Our analysis leverages the inherent modularity of both techniques.
Submission history
From: Aleksandrs Slivkins [view email][v1] Mon, 14 Nov 2022 16:08:44 UTC (23 KB)
[v2] Mon, 20 Mar 2023 22:13:29 UTC (43 KB)
[v3] Fri, 24 Mar 2023 19:45:48 UTC (43 KB)
[v4] Mon, 12 Jun 2023 01:43:30 UTC (44 KB)
[v5] Sat, 29 Jun 2024 08:39:56 UTC (58 KB)
[v6] Thu, 1 Aug 2024 11:49:04 UTC (60 KB)
[v7] Fri, 18 Oct 2024 03:00:10 UTC (62 KB)
Current browse context:
cs.LG
References & Citations
Bibliographic and Citation Tools
Bibliographic Explorer (What is the Explorer?)
Connected Papers (What is Connected Papers?)
Litmaps (What is Litmaps?)
scite Smart Citations (What are Smart Citations?)
Code, Data and Media Associated with this Article
alphaXiv (What is alphaXiv?)
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub (What is DagsHub?)
Gotit.pub (What is GotitPub?)
Hugging Face (What is Huggingface?)
Papers with Code (What is Papers with Code?)
ScienceCast (What is ScienceCast?)
Demos
Recommenders and Search Tools
Influence Flower (What are Influence Flowers?)
CORE Recommender (What is CORE?)
IArxiv Recommender
(What is IArxiv?)
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.