Summary of Merit-based Fair Combinatorial Semi-bandit with Unrestricted Feedback Delays, by Ziqun Chen et al.
Merit-based Fair Combinatorial Semi-Bandit with Unrestricted Feedback Delays
by Ziqun Chen, Kechao Cai, Zhuoyue Chen, Jinbei Zhang, John C.S. Lui
First submitted to arxiv on: 22 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: 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 presents novel bandit algorithms for stochastic combinatorial semi-bandit problems under merit-based fairness constraints, considering reward-independent and reward-dependent feedback delays. The proposed methods aim to balance the trade-off between expected reward regret and fairness regret in applications like crowdsourcing and online advertising. The algorithms are shown to achieve sublinear regret bounds with dependence on delay distribution quantiles. Experimental results using synthetic and real-world data demonstrate the effectiveness of the proposed approaches. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper explores a new problem in machine learning, called stochastic combinatorial semi-bandit, which is important for applications like online advertising. The researchers develop new algorithms to choose the best options (called arms) under different situations where we might not get immediate feedback. They also make sure that their algorithms are fair and don’t favor one arm over others. The results show that these algorithms work well in practice. |
Keywords
* Artificial intelligence * Machine learning
