Summary of Linear Submodular Maximization with Bandit Feedback, by Wenjing Chen et al.
Linear Submodular Maximization with Bandit Feedback
by Wenjing Chen, Victoria G. Crawford
First submitted to arxiv on: 2 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Data Structures and Algorithms (cs.DS)
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 proposes approximation algorithms for maximizing a submodular objective function with noisy queries. The function is a sum of linear functions, where coefficients are unknown but the linear functions themselves can be accessed via value oracle access. Inspired by adaptive allocation algorithms in best-arm identification for linear bandits, the proposed algorithms provide guarantees arbitrarily close to the optimal setting. Experimental results show significant improvements in sample efficiency compared to non-exploiting algorithms on instances of move recommendation. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about finding the best way to combine different things to get a good result. It’s like choosing the best movie to watch, but instead of movies, it’s combinations of different features or characteristics. The problem is that we don’t know how good each feature is by itself, and we can only ask for feedback on our choices in a noisy way. The paper proposes new ways to solve this problem that are more efficient than previous methods. This could be useful in things like recommending movies or summarizing data. |
Keywords
* Artificial intelligence * Objective function
