111 citations · 403 across the 22 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
cs.LG2021★ 1 cited
Explaining generalization in deep learning: progress and fundamental limits
Vaishnavh Nagarajan
This dissertation studies a fundamental open challenge in deep learning theory: why do deep networks generalize well even while being overparameterized, unregularized and fitting t…
cs.LG2021★ 19 cited
Assessing Generalization of SGD via Disagreement
Yiding Jiang, Vaishnavh Nagarajan, Christina Baek +1
We empirically show that the test error of deep networks can be estimated by simply training the same architecture on the same training set but with a different run of Stochastic G…