Improving First and Second-Order Methods by Modeling Uncertainty

By Nicolas Le Roux, Yoshua Bengio, Andrew William Fitzgibbon. 2010

21 citations recorded by the source corpus.

Subfields: Management Science and Operations Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Management Science and Operations Research

1. Yoshua Bengio
2. Jonathan Taylor
3. Sebastian Nowozin
4. Christian Daniel

Citations in the corpus

• Practical Recommendations for Gradient-Based Training of Deep Architectures (2012, background): “Diag-onal and low-rank online approximations of natural gradient (Le Roux et al. , 2008; Le Roux et al. , 2011) have been proposed and shown to speed-up training in some contexts.”
• Learning Step Size Controllers for Robust Neural Network Training (2016, background): “TONGA (Le Roux, Bengio, and Fitzgibbon 2012) models the uncertainty in the weight update by building a model of the gradients.”