Timezone: »

 
Spotlight
Logarithmic Pruning is All You Need
Laurent Orseau · Marcus Hutter · Omar Rivasplata

Tue Dec 08 08:20 AM -- 08:30 AM (PST) @ Orals & Spotlights: Dynamical Sys/Density/Sparsity

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.

Author Information

Laurent Orseau (DeepMind)
Marcus Hutter (DeepMind)
Omar Rivasplata (DeepMind & UCL)

I studied maths at the Pontificia Universidad Catolica del Peru (BSc 2000) and the University of Alberta (MSc 2005, PhD 2012). I joined Csaba Szepesvari's team at U of A Computing Science in 2016 to start working on machine learning, and in 2017 I moved to the UK to join John Shawe-Taylor's team at UCL Computer Science. Since 2018 I am also affiliated with the Foundations Team at DeepMind. I am very interested in machine learning theory, probability and statistics.

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

More from the Same Authors