\dm_csml_event_details UCL ELLIS

Feature Learning in Infinite-Width Neural Networks


Speaker

Greg Yang

Affiliation

Microsoft Research

Date

Friday, 26 February 2021

Time

17:00-18:00

Location

https://ucl.zoom.us/s/99166798620

Event series

DeepMind/ELLIS CSML Seminar Series

Summary

Abstract: As its width tends to infinity, a deep neural network's behavior under gradient descent can become simplified and predictable (e.g. given by the Neural Tangent Kernel (NTK)), if it is parametrized appropriately (e.g. the NTK parametrization). However, we show that the standard and NTK parametrizations of a neural network do not admit infinite-width limits that can learn representations (i.e. features), which is crucial for pretraining and transfer learning such as with BERT. We propose simple modifications to the standard parametrization to allow for feature learning in the limit. Using the *Tensor Programs* technique, we derive explicit formulas for such limits. On Word2Vec and few-shot learning on Omniglot via MAML, two canonical tasks that rely crucially on feature learning, we compute these limits exactly. We find that they outperform both NTK baselines and finite-width networks, with the latter approaching the infinite-width feature learning performance as width increases.

More generally, we classify a natural space of neural network parametrizations that generalizes standard, NTK, and Mean Field parametrizations. We show 1) any parametrization in this space either admits feature learning or has an infinite-width training dynamics given by kernel gradient descent, but not both; 2) any such infinite-width limit can be computed using the Tensor Programs technique.

This work is based on https://arxiv.org/abs/2011.14522.

iCalendar

csml_id_421.ics