Compressibility and Generalization in Large-Scale Deep Learning

By Wenda Zhou, Victor Veitch, Morgane Austern, Ryan P. Adams, Peter Orbanz. 2018

18 citations recorded by the source corpus.

Subfields: Efficiency & Compression, Scaling & Learning Theory

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Efficiency & Compression

1. Dan Feldman
2. Daniela Rus
3. Yuanzhi Li
4. Lucas Liebenwein
5. Yingyu Liang
6. Cenk Baykal
7. Lingao Xiao
8. Yang He

In Scaling & Learning Theory

1. Yuanzhi Li
2. Yingyu Liang
3. Dan Feldman
4. Zeyuan Allen-Zhu
5. Quanquan Gu
6. Simon Shaolei Du
7. Tengyu Ma
8. Jason D. Lee

Citations in the corpus

• Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data (2018, background): “[3, 23, 21] proved spectrally-normalized margin-based generalization bounds, [9, 23] derived bounds from a PAC-Bayes approach, and [1, 33, 4] derived bounds from the compression point of view.”
• Data-Dependent Coresets for Compressing Neural Networks with Applications to Generalization Bounds (2018, background): “[48] highlighted the close connection between compressibility and generalization of neural networks.”