collaborators

5 papers

cs.LG2019

REVE: Regularizing Deep Learning with Variational Entropy Bound

Antoine Saporta, Yifu Chen, Michael Blot +1

Studies on generalization performance of machine learning algorithms under the scope of information theory suggest that compressed representations can guarantee good generalization…

cs.LG2019

A Characterization of Mean Squared Error for Estimator with Bagging

Martin Mihelich, Charles Dognin, Yan Shu +1

Bagging can significantly improve the generalization performance of unstable machine learning algorithms such as trees or neural networks. Though bagging is now widely used in prac…

stat.ML2018

SHADE: Information Based Regularization for Deep Learning

Michael Blot, Thomas Robert, Nicolas Thome +1

Regularization is a big issue for training deep neural networks. In this paper, we propose a new information-theory-based regularization scheme named SHADE for SHAnnon DEcay. The o…

stat.ML2018

SHADE: Information-Based Regularization for Deep Learning

Michael Blot, Thomas Robert, Nicolas Thome +1

Regularization is a big issue for training deep neural networks. In this paper, we propose a new information-theory-based regularization scheme named SHADE for SHAnnon DEcay. The o…

cs.LG2018

GoSGD: Distributed Optimization for Deep Learning with Gossip Exchange

Michael Blot, David Picard, Matthieu Cord

We address the issue of speeding up the training of convolutional neural networks by studying a distributed method adapted to stochastic gradient descent. Our parallel optimization…