Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data

By Gintare Karolina Dziugaite, Daniel M. Roy. 2017

967 citations recorded by the source corpus.

One of the defining properties of deep learning is that models are chosen to have many more parameters than available training data. In light of this capacity for overfitting, it is remarkable that simple algorithms like SGD reliably return solutions with low test error. One roadblock to explaining these phenomena in terms of implicit regularization, structural properties of the solution, and/or easiness of the data is that many learning bounds are quantitatively vacuous when applied to networks learned by SGD in this "deep learning" regime. Logically, in order to explain generalization, we need nonvacuous bounds. We return to an idea by Langford and Caruana (2001), who used PAC-Bayes bounds to compute nonvacuous numerical bounds on generalization error for stochastic two-layer two-hidden-unit neural networks via a sensitivity analysis. By optimizing the PAC-Bayes bound directly, we are able to extend their approach and obtain nonvacuous generalization bounds for deep stochastic neural network classifiers with millions of parameters trained on only tens of thousands of examples. We connect our findings to recent and old work on flat minima and MDL-based explanations of generalization.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

  1. Yoshua Bengio
  2. Sergey Levine
  3. Ruslan Salakhutdinov
  4. Percy Liang
  5. Quoc V. Le
  6. Mohit Bansal
  7. Jianfeng Gao
  8. Luke S. Zettlemoyer

In Scaling & Learning Theory

  1. Yuanzhi Li
  2. Tengyu Ma
  3. Jason D. Lee
  4. Samet Oymak
  5. Behnam Neyshabur
  6. Colin Wei
  7. Quanquan Gu
  8. Greg Yang

Citations in the corpus