Summary of No Free Prune: Information-theoretic Barriers to Pruning at Initialization, by Tanishq Kumar et al.
No Free Prune: Information-Theoretic Barriers to Pruning at Initialization
by Tanishq Kumar, Kevin Luo, Mark Sellke
First submitted to arxiv on: 2 Feb 2024
Categories
- Main: Machine Learning (stat.ML)
- Secondary: 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 This research paper investigates the relationship between large models and deep learning. The concept of “lottery tickets” at or near initialization raises questions about whether sparse networks can be quickly identified and trained without training dense models. However, efforts to find these sparse subnetworks without training the dense model have been unsuccessful. The authors propose a theoretical explanation based on the effective parameter count, showing that a sparse neural network which robustly interpolates noisy data requires a heavily data-dependent mask. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper looks at why some big models are needed for deep learning. It’s like finding a needle in a haystack – you need to train a whole model before you can find the good parts that make it work well. The researchers came up with an idea about how this works and did some tests on computers to prove it. |
Keywords
* Artificial intelligence * Deep learning * Mask * Neural network
