Summary of Practical Multi-fidelity Machine Learning: Fusion Of Deterministic and Bayesian Models, by Jiaxiang Yi et al.
Practical multi-fidelity machine learning: fusion of deterministic and Bayesian models
by Jiaxiang Yi, Ji Cheng, Miguel A. Bessa
First submitted to arxiv on: 21 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Probability (math.PR); 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 This paper proposes a multi-fidelity machine learning strategy that integrates scarce high-fidelity data with abundant low-fidelity data to address the accuracy-efficiency trade-off. The approach combines a non-probabilistic regression model for low-fidelity data with a Bayesian model for high-fidelity data, trained in a staggered scheme. The resulting prediction includes uncertainty quantification for both noisy and noiseless multi-fidelity data. The strategy unifies various modeling choices, including kernel ridge regression and Gaussian processes, or deep neural networks and Bayesian neural networks. Numerical examples demonstrate the effectiveness and efficiency of the proposed strategies compared to state-of-the-art methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about using machine learning to combine different types of data. Sometimes we have a lot of low-quality data that’s easy to get, but it’s not very accurate. Other times we have a little high-quality data that’s hard to get, but it’s really accurate. The authors suggest a way to mix these two types of data together to get a better result. They use different models for the low-quality and high-quality data, and then combine them in a special way. This makes their method easy to use and practical for many real-world problems. |
Keywords
» Artificial intelligence » Machine learning » Regression
