23 citations · 40 across the 6 of their papers we have counts for
Showing stat.MLShow all
2 papers · 1 filter
stat.ML2019★ 23 cited
Multi-Domain Adversarial Learning
Alice Schoenauer-Sebag, Louise Heinrich, Marc Schoenauer +3
Multi-domain learning (MDL) aims at obtaining a model with minimal average risk across multiple domains. Our empirical motivation is automated microscopy data, where cultured cells…
stat.ML2017★ 10 cited
Stochastic Gradient Descent: Going As Fast As Possible But Not Faster
Alice Schoenauer-Sebag, Marc Schoenauer, Michèle Sebag
When applied to training deep neural networks, stochastic gradient descent (SGD) often incurs steady progression phases, interrupted by catastrophic episodes in which loss and grad…