Summary of Rethinking Log Odds: Linear Probability Modelling and Expert Advice in Interpretable Machine Learning, by Danial Dervovic and Nicolas Marchesotti and Freddy Lecue and Daniele Magazzeni
Rethinking Log Odds: Linear Probability Modelling and Expert Advice in Interpretable Machine Learning
by Danial Dervovic, Nicolas Marchesotti, Freddy Lecue, Daniele Magazzeni
First submitted to arxiv on: 11 Nov 2022
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
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 proposed family of interpretable machine learning models introduces two novel additions: Linearised Additive Models (LAMs) and SubscaleHedge, an expert advice algorithm for combining base models trained on subsets of features. LAMs replace the traditional logistic link function in General Additive Models (GAMs), enabling direct global and local attributions of additive components to the model output in probability space. This paper demonstrates that LAMs and SubscaleHedge improve the interpretability of their base algorithms without sacrificing performance, as shown through rigorous null-hypothesis significance testing on financial modelling data. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research introduces two new machine learning models: Linearised Additive Models (LAMs) and SubscaleHedge. These models help us understand how they work and why the predictions are made. The goal is to make AI more transparent and reliable. The scientists tested their models on financial data and found that they performed well without sacrificing accuracy. |
Keywords
* Artificial intelligence * Machine learning * Probability
