23 citations · 31 across the 4 of their papers we have counts for
Showing 2020Show all
2 papers · 1 filter
cs.LG2020★ 2 cited
Making Coherence Out of Nothing At All: Measuring the Evolution of Gradient Alignment
Satrajit Chatterjee, Piotr Zielinski
We propose a new metric (-coherence) to experimentally study the alignment of per-example gradients during training. Intuitively, given a sample of size , -coherence is th…
cs.LG2020★ 5 cited
Weak and Strong Gradient Directions: Explaining Memorization, Generalization, and Hardness of Examples at Scale
Piotr Zielinski, Shankar Krishnan, Satrajit Chatterjee
Coherent Gradients (CGH) is a recently proposed hypothesis to explain why over-parameterized neural networks trained with gradient descent generalize well even though they have suf…