Summary of Neural Quasiprobabilistic Likelihood Ratio Estimation with Negatively Weighted Data, by Matthew Drnevich et al.
Neural Quasiprobabilistic Likelihood Ratio Estimation with Negatively Weighted Data
by Matthew Drnevich, Stephen Jiggins, Judith Katzy, Kyle Cranmer
First submitted to arxiv on: 14 Oct 2024
Categories
- Main: Machine Learning (stat.ML)
- Secondary: Machine Learning (cs.LG); High Energy Physics – Experiment (hep-ex)
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, researchers develop a novel framework for likelihood-ratio estimation in quasiprobabilistic settings, where probability densities can be negative. This extension is motivated by real-world scenarios in high-energy particle physics. The authors propose two strategies to overcome the challenges posed by negative densities and weights: a novel loss function and a new model architecture based on signed mixture models. They demonstrate their approach using pedagogical and real-world examples from particle physics. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about finding ways to estimate likelihood ratios when probability densities can be negative. This is important in high-energy particle physics, where scientists need to understand the probabilities of different outcomes. The authors come up with two new ideas to solve this problem: a special way to measure how good their model is and a new type of machine learning model. They test these ideas using simple and real-world examples. |
Keywords
» Artificial intelligence » Likelihood » Loss function » Machine learning » Probability
