Summary of Online Uniform Sampling: Randomized Learning-augmented Approximation Algorithms with Application to Digital Health, by Xueqing Liu et al.
Online Uniform Sampling: Randomized Learning-Augmented Approximation Algorithms with Application to Digital Health
by Xueqing Liu, Kyra Gan, Esmaeil Keyvanshokooh, Susan Murphy
First submitted to arxiv on: 3 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Optimization and Control (math.OC)
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 paper addresses a novel problem in digital health, online uniform sampling (OUS), where an algorithm must distribute a budget uniformly across unknown decision times. Given a budget and time horizon, the algorithm must determine sampling probabilities to maximize spending while achieving a uniform distribution. The authors propose two algorithms: a randomized algorithm and its extension with learning augmentation. These algorithms provide worst-case approximation guarantees and are evaluated through synthetic experiments and a real-world case study involving the HeartSteps mobile application. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper studies how to share a limited budget evenly across unknown times when making decisions online. The goal is to make good choices while using up the budget in an even way over time. The authors created two new algorithms that work well and can be used to solve this problem. They tested these algorithms on fake data and real-world data from the HeartSteps app. |
