Summary of Accelerating Approximate Thompson Sampling with Underdamped Langevin Monte Carlo, by Haoyang Zheng et al.
Accelerating Approximate Thompson Sampling with Underdamped Langevin Monte Carlo
by Haoyang Zheng, Wei Deng, Christian Moya, Guang Lin
First submitted to arxiv on: 22 Jan 2024
Categories
- Main: Machine Learning (stat.ML)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
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 In this paper, the authors propose an approximate Thompson sampling strategy that uses underdamped Langevin Monte Carlo to address scalability issues in high-dimensional problems. By leveraging standard smoothness and log-concavity conditions, they design a potential function that improves the sample complexity for realizing logarithmic regrets from O(d) to O(sqrt(d)). The authors empirically validate the scalability and robustness of their algorithm through synthetic experiments in high-dimensional bandit problems. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine you’re trying to make decisions based on incomplete information. This paper shows how to do it more efficiently, even when there’s a lot of data involved. They developed a new way to use an old idea called Thompson sampling, which helps us choose the best option given what we know so far. The authors found that their method is much faster and more reliable than before, making it useful for real-world applications. |
