Summary of P-mean Regret For Stochastic Bandits, by Anand Krishna et al.
p-Mean Regret for Stochastic Bandits
by Anand Krishna, Philips George John, Adarsh Barik, Vincent Y. F. Tan
First submitted to arxiv on: 14 Dec 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computer Science and Game Theory (cs.GT)
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 This research extends the concept of p-mean welfare objective from social choice theory to study p-mean regret in stochastic multi-armed bandit problems. The p-mean regret, defined as the difference between the optimal mean among the arms and the p-mean of expected rewards, provides a flexible framework for evaluating bandit algorithms. By adjusting the parameter p, algorithm designers can balance fairness and efficiency. Our framework includes both average cumulative regret and Nash regret as special cases. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study takes a math problem called “stochastic multi-armed bandits” to a new level by using a tool from economics called the p-mean welfare objective. This lets us measure how well different algorithms do in this problem, with an option to balance fairness and efficiency by adjusting one number (p). This framework includes two important types of regrets as special cases. |
