activity
20172022
most citedThe State of Sparsity in Deep Neural Networks

439 citations · 1.2k across the 10 of their papers we have counts for

collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG202121 cited

Top-KAST: Top-K Always Sparse Training

Siddhant M. Jayakumar, Razvan Pascanu, Jack W. Rae +2

Sparse neural networks are becoming increasingly important as the field seeks to improve the performance of existing models by scaling them up, while simultaneously trying to reduc…

cs.LG202022 cited

On the Generalization Benefit of Noise in Stochastic Gradient Descent

Samuel L. Smith, Erich Elsen, Soham De

It has long been argued that minibatch stochastic gradient descent can generalize better than large batch gradient descent in deep neural networks. However recent papers have quest…

cs.LG2020

AlgebraNets

Jordan Hoffmann, Simon Schmitt, Simon Osindero +2

Neural networks have historically been built layerwise from the set of functions in , i.e. with activations and weights/parameters represented…

cs.LG20203 cited

A Practical Sparse Approximation for Real Time Recurrent Learning

Jacob Menick, Erich Elsen, Utku Evci +3

Current methods for training recurrent neural networks are based on backpropagation through time, which requires storing a complete history of network states, and prohibits updatin…

cs.LG2020

Sparse GPU Kernels for Deep Learning

Trevor Gale, Matei Zaharia, Cliff Young +1

Scientific workloads have traditionally exploited high levels of sparsity to accelerate computation and reduce memory requirements. While deep neural networks can be made sparse, a…

cs.LG2019

The Difficulty of Training Sparse Neural Networks

Utku Evci, Fabian Pedregosa, Aidan Gomez +1

We investigate the difficulties of training sparse neural networks and make new observations about optimization dynamics and the energy landscape within the sparse regime. Recent w…