Summary of Supervised Contrastive Representation Learning: Landscape Analysis with Unconstrained Features, by Tina Behnia et al.
Supervised Contrastive Representation Learning: Landscape Analysis with Unconstrained Features
by Tina Behnia, Christos Thrampoulidis
First submitted to arxiv on: 29 Feb 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 The paper investigates the phenomenon of neural-collapse in deep neural networks trained with contrastive loss, specifically supervised contrastive (SC) loss. The authors study the solutions derived from optimizing SC loss using an analytical approach and show that all local minima are global minima, with a unique minimizer up to rotation. They also characterize the properties of global solutions under label-imbalanced training data. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper looks at how deep neural networks work when they’re over-trained and use a special kind of loss function called supervised contrastive (SC) loss. It shows that even though this loss function is tricky, it always finds the same answer. The authors also explore what happens when there’s an imbalance in the training data. |
Keywords
* Artificial intelligence * Contrastive loss * Loss function * Supervised
