72 citations · 542 across the 65 of their papers we have counts for
Showing 2018 · stat.MLShow all
2 papers · 2 filters
stat.ML2018★ 10 cited
Minimum weight norm models do not always generalize well for over-parameterized problems
Vatsal Shah, Anastasios Kyrillidis, Sujay Sanghavi
This work is substituted by the paper in arXiv:2011.14066. Stochastic gradient descent is the de facto algorithm for training deep neural networks (DNNs). Despite its popularity, i…
stat.ML2018★ 1 cited
Implicit regularization and solution uniqueness in over-parameterized matrix sensing
Kelly Geyer, Anastasios Kyrillidis, Amir Kalev
We consider whether algorithmic choices in over-parameterized linear matrix factorization introduce implicit regularization. We focus on noiseless matrix sensing over rank- posi…