Summary of Learning to Schedule Online Tasks with Bandit Feedback, by Yongxin Xu et al.
Learning to Schedule Online Tasks with Bandit Feedback
by Yongxin Xu, Shangshang Wang, Hengquan Guo, Xin Liu, Ziyu Shao
First submitted to arxiv on: 26 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Distributed, Parallel, and Cluster Computing (cs.DC)
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 double-optimistic learning based Robbins-Monro (DOL-RM) algorithm aims to tackle online task scheduling challenges in cloud computing and crowdsourcing. By integrating optimistic estimation for reward-to-cost ratios and implicit learning of task arrival distributions, DOL-RM achieves a sub-linear regret of O(T^(3/4)) while converging to the best cumulative reward-to-cost ratio. This is the first result for online task scheduling under uncertain task arrival distribution and unknown reward and cost. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Online task scheduling is crucial in cloud computing and crowdsourcing, but it’s made tricky by unpredictable system fluctuations and unknown task arrival distributions. A new algorithm called DOL-RM tries to solve this problem by learning how to schedule tasks effectively. It does this by estimating the rewards and costs of different tasks and figuring out how tasks arrive over time. The result is a way to make good decisions about scheduling tasks, even when things are uncertain. |
