R.I.P.
👻
Ghosted
Size-Independent Sample Complexity of Neural Networks
December 18, 2017 · Declared Dead · 🏛 Annual Conference Computational Learning Theory
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Noah Golowich, Alexander Rakhlin, Ohad Shamir
arXiv ID
1712.06541
Category
cs.LG: Machine Learning
Cross-listed
cs.NE,
stat.ML
Citations
602
Venue
Annual Conference Computational Learning Theory
Last Checked
2 months ago
Abstract
We study the sample complexity of learning neural networks, by providing new bounds on their Rademacher complexity assuming norm constraints on the parameter matrix of each layer. Compared to previous work, these complexity bounds have improved dependence on the network depth, and under some additional assumptions, are fully independent of the network size (both depth and width). These results are derived using some novel techniques, which may be of independent interest.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
📜 Similar Papers
In the same crypt — Machine Learning
R.I.P.
👻
Ghosted
XGBoost: A Scalable Tree Boosting System
R.I.P.
👻
Ghosted
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
R.I.P.
👻
Ghosted
Semi-Supervised Classification with Graph Convolutional Networks
R.I.P.
👻
Ghosted
Proximal Policy Optimization Algorithms
R.I.P.
👻
Ghosted
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Died the same way — 👻 Ghosted
R.I.P.
👻
Ghosted
Language Models are Few-Shot Learners
R.I.P.
👻
Ghosted
You Only Look Once: Unified, Real-Time Object Detection
R.I.P.
👻
Ghosted
A Unified Approach to Interpreting Model Predictions
R.I.P.
👻
Ghosted