Summary of Rethinking Test-time Likelihood: the Likelihood Path Principle and Its Application to Ood Detection, by Sicong Huang et al.
Rethinking Test-time Likelihood: The Likelihood Path Principle and Its Application to OOD Detection
by Sicong Huang, Jiawei He, Kry Yik Chau Lui
First submitted to arxiv on: 10 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: 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 In this paper, researchers tackle the issue of estimating likelihood by deep generative models (DGMs), which often perform poorly in out-of-distribution (OOD) detection. While some recent works have proposed alternative scores and achieved better results, these solutions lack provable guarantees and it’s unclear what information they extract. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Deep learning models are used to generate data that resembles real-world scenarios. However, when faced with new, unseen data, these models often struggle to determine whether the data is genuine or not. The paper explores ways to improve this “out-of-distribution” detection by developing better likelihood estimates. The authors test different methods and show how they can be used to make more accurate predictions. |
Keywords
* Artificial intelligence * Deep learning * Likelihood
