Summary of Demystifying Spectral Bias on Real-world Data, by Itay Lavie and Zohar Ringel
Demystifying Spectral Bias on Real-World Data
by Itay Lavie, Zohar Ringel
First submitted to arxiv on: 4 Jun 2024
Categories
- Main: Machine Learning (stat.ML)
- Secondary: Disordered Systems and Neural Networks (cond-mat.dis-nn); Machine Learning (cs.LG)
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 explore the relationship between kernel ridge regression (KRR), Gaussian processes (GPs), and highly over-parameterized deep neural networks. They show that the learnability of a target function is directly tied to the eigenvalues of the kernel sampled on the input data distribution. The authors then propose using eigenvalues and eigenfunctions associated with idealized data measures to reveal spectral bias on complex datasets, allowing for bounds on learnability on real-world data. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper explains how KRR and GPs can be used to improve deep neural networks. It’s all about understanding what makes some things easier or harder to learn, using special mathematical tools called eigenvalues. The researchers found a way to use these tools to figure out why certain datasets are more or less learnable, and this could help us make better artificial intelligence. |
Keywords
» Artificial intelligence » Regression
