Timezone: »

Anticorrelated Noise Injection for Improved Generalization
Antonio Orvieto · Hans Kersting · Frank Proske · Francis Bach · Aurelien Lucchi

Tue Jul 19 02:30 PM -- 02:35 PM (PDT) @ Room 309

Injecting artificial noise into gradient descent (GD) is commonly employed to improve the performance of machine learning models. Usually, uncorrelated noise is used in such perturbed gradient descent (PGD) methods. It is, however, not known if this is optimal or whether other types of noise could provide better generalization performance. In this paper, we zoom in on the problem of correlating the perturbations of consecutive PGD steps. We consider a variety of objective functions for which we find that GD with anticorrelated perturbations ("Anti-PGD") generalizes significantly better than GD and standard (uncorrelated) PGD. To support these experimental findings, we also derive a theoretical analysis that demonstrates that Anti-PGD moves to wider minima, while GD and PGD remain stuck in suboptimal regions or even diverge. This new connection between anticorrelated noise and generalization opens the field to novel ways to exploit noise for training machine learning models.

Author Information

Antonio Orvieto (ETH Zurich)
Hans Kersting (INRIA and ENS Paris)
Frank Proske (University of Oslo)
Francis Bach (INRIA - Ecole Normale Supérieure)
Aurelien Lucchi (ETH Zurich)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors