Summary of The Exploration Of Neural Collapse Under Imbalanced Data, by Haixia Liu
The Exploration of Neural Collapse under Imbalanced Data
by Haixia Liu
First submitted to arxiv on: 26 Nov 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Optimization and Control (math.OC)
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 research investigates neural collapse, a phenomenon observed in trained model solutions. In the context of imbalanced datasets, this study examines the L-extended unconstrained feature model with a bias term and provides a theoretical analysis of its global minimizers. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper looks at something called “neural collapse” that happens when we train models on data with different amounts of information. They’re studying a special kind of model that tries to find the best solution, and they want to understand how it works when the data is unfair. |
