Summary of Noether’s Razor: Learning Conserved Quantities, by Tycho F. A. Van Der Ouderaa et al.
Noether’s razor: Learning Conserved Quantities
by Tycho F. A. van der Ouderaa, Mark van der Wilk, Pim de Haan
First submitted to arxiv on: 10 Oct 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 research paper, the authors leverage Noether’s theorem to parameterize symmetries as learnable conserved quantities in machine learning models. They introduce a novel approach that learns conserved quantities and associated symmetries directly from train data through approximate Bayesian model selection, jointly with regular training procedures. The method derives a variational lower bound to the marginal likelihood as its training objective, which embodies an Occam’s Razor effect that avoids trivial conservation laws without manual tuning of additional regularizers. The authors demonstrate their approach on n-harmonic oscillators and n-body systems, achieving improved predictive accuracy and overall performance. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper uses math and computers to help machines learn from data better. It takes a famous idea called Noether’s theorem and uses it to teach machines about symmetries in the data. The machine then learns how to keep these symmetries as it trains on more data. This helps the machine make better predictions and understand the world better. |
Keywords
* Artificial intelligence * Likelihood * Machine learning
