Summary of Principled Bayesian Optimisation in Collaboration with Human Experts, by Wenjie Xu et al.
Principled Bayesian Optimisation in Collaboration with Human Experts
by Wenjie Xu, Masaki Adachi, Colin N. Jones, Michael A. Osborne
First submitted to arxiv on: 14 Oct 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 The paper presents a novel Bayesian optimization framework for real-world problems that integrates domain expertise from human experts. The approach optimizes the process by leveraging binary accept/reject recommendations (labels) from experts, while minimizing the number of expert labels required to achieve efficient convergence. The introduced principled method guarantees two key properties: handover guarantee and no-harm guarantee with data-driven trust level adjustment. This adaptive trust level ensures that the convergence rate will not be worse than without using advice, even in adversarial scenarios. Empirical results demonstrate the outperformance of existing baselines in battery design tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about a new way to get help from experts when trying to find the best solution for real-world problems. Experts give advice on what to try next, but their opinions can be wrong or expensive to obtain. The new method makes sure that we don’t waste expert time or effort and also works even if the experts are giving bad advice. It’s tested with people designing batteries and shows it’s better than other methods. |
Keywords
* Artificial intelligence * Optimization
