Researchers have developed a novel method for online submodular minimization using bandit feedback, which is designed to track a moving minimizer over time. This new approach utilizes a zeroth-order oracle based on the Lovász extension, with evaluations on perturbed and base points. The method establishes dynamic regret bounds of order O((1+sqrt(P*_N))N^3/4) in general and O((1+sqrt(P*_N))N^2/3) under specific drift conditions, outperforming existing algorithms numerically. AI
IMPACT Introduces a novel method for online submodular minimization with improved dynamic regret bounds, potentially advancing optimization techniques in dynamic environments.
RANK_REASON The cluster contains a research paper submitted to arXiv detailing a new algorithmic method. [lever_c_demoted from research: ic=1 ai=1.0]
- alphaXiv
- Amir Ali Farzin
- arXiv
- arXivLabs
- Bandit Online Submodular Minimisation Using Zeroth-Order Oracles
- CatalyzeX Code Finder for Papers
- CORE Recommender
- DagsHub
- Gotit.pub
- Hazan and Kale (2012)
- Hugging Face
- Lovász extension
- ScienceCast
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →