Timezone: »

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

Tue Dec 08 09:00 AM -- 11:00 AM (PST) @ Poster Session 1 #297

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)

My top-level areas of interest are statistical learning theory, machine learning, probability and statistics. These days I am very interested in deep learning and reinforcement learning. I am affiliated with the Institute for Mathematical and Statistical Sciences, University College London, hosted by the Department of Statistical Science as a Senior Research Fellow. Before my current post I was at UCL Mathematics for a few months, and previously I was at UCL Computer Science for a few years, where I did research studies (machine learning) sponsored by DeepMind and in parallel I was a research scientist intern at DeepMind for three years. Back in the day I studied undergraduate maths (BSc 2000, Pontificia Universidad Católica del Perú) and graduate maths (MSc 2005, PhD 2012, University of Alberta). I've lived in Peru, in Canada, and now I'm based in the UK.

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

More from the Same Authors