pith. sign in

Statistical learning: Stability is sufficient for generalization and necessary and sufficient for consistency of empirical risk min- imization

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2016 1

verdicts

ACCEPT 1

representative citing papers

Understanding deep learning requires rethinking generalization

cs.LG · 2016-11-10 · accept · novelty 8.0

State-of-the-art convolutional networks easily memorize random labels and unstructured noise images, indicating that generalization in deep learning cannot be explained by traditional capacity or regularization arguments.

citing papers explorer

Showing 1 of 1 citing paper.

  • Understanding deep learning requires rethinking generalization cs.LG · 2016-11-10 · accept · none · ref 3

    State-of-the-art convolutional networks easily memorize random labels and unstructured noise images, indicating that generalization in deep learning cannot be explained by traditional capacity or regularization arguments.