Pushing the bounds of dropout

By Gábor Melis, Charles Blundell, Tomás Kociský, Karl Moritz Hermann, Chris Dyer, Phil Blunsom. 2018

13 citations recorded by the source corpus.

We show that dropout training is best understood as performing MAP estimation concurrently for a family of conditional models whose objectives are themselves lower bounded by the original dropout objective. This discovery allows us to pick any model from this family after training, which leads to a substantial improvement on regularisation-heavy language modelling. The family includes models that compute a power mean over the sampled dropout masks, and their less stochastic subvariants with tighter and higher lower bounds than the fully stochastic dropout objective. We argue that since the deterministic subvariant's bound is equal to its objective, and the highest amongst these models, the predominant view of it as a good approximation to MC averaging is misleading. Rather, deterministic dropout is the best available approximation to the true objective.

Subfields: Artificial Intelligence

How researchers see this paper

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

In Artificial Intelligence

Citations in the corpus

Improving Neural Language Models by Segmenting, Attending, and Predicting the Future (2019, methodology): “Similarly, applying more careful dropout strategies can also improve the language models (Gal and Ghahramani, 2016; Melis et al., 2018).”