4.7k citations · 5.1k across the 10 of their papers we have counts for
Showing 2017Show all
2 papers · 1 filter
cs.LG2017★ 4.7k cited
mixup: Beyond Empirical Risk Minimization
Hongyi Zhang, Moustapha Cisse, Yann N. Dauphin +1
Large deep neural networks are powerful, but exhibit undesirable behaviors such as memorization and sensitivity to adversarial examples. In this work, we propose mixup, a simple le…
stat.ML2017★ 9 cited
Matrix Completion from Samples in Linear Time
David Gamarnik, Quan Li, Hongyi Zhang
We consider the problem of reconstructing a rank- matrix from a sampling of its entries. Under a certain incoherence assumption on and for the case when bot…