This is the public, feature-limited version of the conference webpage. After Registration and login please visit the full version.

Logarithmic Pruning is All You Need

Laurent Orseau, Marcus Hutter, Omar Rivasplata

Spotlight presentation: Orals & Spotlights Track 06: Dynamical Sys/Density/Sparsity
on 2020-12-08T08:20:00-08:00 - 2020-12-08T08:30:00-08:00
Poster Session 2 (more posters)
on 2020-12-08T09:00:00-08:00 - 2020-12-08T11:00:00-08:00
Abstract: The Lottery Ticket Hypothesis is a conjecture that every large neural network contains a subnetwork that, when trained in isolation, achieves comparable performance to the large network. An even stronger conjecture has been proven recently: Every sufficiently overparameterized network contains a subnetwork that, even without training, achieves comparable accuracy to the trained large network. This theorem, however, relies on a number of strong assumptions and guarantees a polynomial factor on the size of the large network compared to the target function. In this work, we remove the most limiting assumptions of this previous work while providing significantly tighter bounds: the overparameterized network only needs a logarithmic factor (in all variables but depth) number of neurons per weight of the target subnetwork.

Preview Video and Chat

To see video, interact with the author and ask questions please use registration and login.