Summary of Multi-armed Bandits with Network Interference, by Abhineet Agarwal et al.
Multi-Armed Bandits with Network Interference
by Abhineet Agarwal, Anish Agarwal, Lorenzo Masoero, Justin Whitehouse
First submitted to arxiv on: 28 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Methodology (stat.ME); 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 proposed paper tackles the problem of adaptive treatment assignment in online marketplaces, where the revenue of a good depends on discounts applied to competing goods. The authors formulate this as a multi-armed bandit (MAB) problem, where a learner sequentially assigns one of possible actions (discounts) to units (goods) over rounds to minimize regret. Unlike traditional MAB problems, the reward of each unit depends on the treatments assigned to other units, introducing interference across the underlying network of units. To overcome this issue, the authors propose simple, linear regression-based algorithms that achieve provably low regret. These algorithms generalize previous works by relaxing conditions on the strength of interference on a known network. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper studies how to adaptively assign discounts in online marketplaces to maximize revenue. This is done by using a special type of math problem called multi-armed bandit, where you make many decisions based on incomplete information. In this case, each decision affects the outcome for many different products. The authors develop new algorithms that work well even when we don’t know exactly how much each product will be affected by each other. |
Keywords
» Artificial intelligence » Linear regression
