Summary of Logarithmic Regret For Unconstrained Submodular Maximization Stochastic Bandit, by Julien Zhou (thoth et al.
Logarithmic Regret for Unconstrained Submodular Maximization Stochastic Bandit
by Julien Zhou, Pierre Gaillard, Thibaud Rahier, Julyan Arbel
First submitted to arxiv on: 11 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Combinatorics (math.CO); Optimization and Control (math.OC); Machine Learning (stat.ML)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper addresses the online unconstrained submodular maximization problem (Online USM) with stochastic bandit feedback. The goal is to maximize a non-monotone submodular function with noisy rewards in a bounded interval. Double-Greedy – Explore-then-Commit (DG-ETC) is proposed, adapting from offline and online full-information settings. DG-ETC achieves a O(d(dT)) problem-dependent upper bound for the 1/2-approximate pseudo-regret and a O(dT{2/3}(dT){1/3}) problem-free one, outperforming existing approaches. The paper introduces a problem-dependent notion of hardness characterizing the transition between logarithmic and polynomial regime for the upper bounds. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper solves a problem called online unconstrained submodular maximization with noisy rewards. It’s like trying to find the best way to allocate resources, but you don’t know exactly how good each choice will be. The authors propose a new approach that works well in this situation and compare it to other methods. Their method is able to make good choices even when there’s a lot of uncertainty. |
