54 citations · 227 across the 36 of their papers we have counts for
Showing 2017 · stat.MLShow all
2 papers · 2 filters
stat.ML2017★ 22 cited
Causal Generative Neural Networks
Olivier Goudet, Diviyan Kalainathan, Philippe Caillou +3
We present Causal Generative Neural Networks (CGNNs) to learn functional causal models from observational data. CGNNs leverage conditional independencies and distributional asymmet…
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…