Erich Elsen

is this you? claim profile

∙ 0 followers
Google

On the Generalization Benefit of Noise in Stochastic Gradient Descent

It has long been argued that minibatch stochastic gradient descent can g...
06/26/2020 ∙ by Samuel L. Smith, et al. ∙ 12 ∙ share

read it
Sparse GPU Kernels for Deep Learning

Scientific workloads have traditionally exploited high levels of sparsit...
06/18/2020 ∙ by Trevor Gale, et al. ∙ 11 ∙ share

read it
AlgebraNets

Neural networks have historically been built layerwise from the set of f...
06/12/2020 ∙ by Jordan Hoffmann, et al. ∙ 0 ∙ share

read it
A Practical Sparse Approximation for Real Time Recurrent Learning

Current methods for training recurrent neural networks are based on back...
06/12/2020 ∙ by Jacob Menick, et al. ∙ 4 ∙ share

read it
End-to-End Adversarial Text-to-Speech

Modern text-to-speech synthesis pipelines typically involve multiple pro...
06/05/2020 ∙ by Jeff Donahue, et al. ∙ 0 ∙ share

read it
Rigging the Lottery: Making All Tickets Winners

Sparse neural networks have been shown to be more parameter and compute ...
11/25/2019 ∙ by Utku Evci, et al. ∙ 0 ∙ share

read it
Fast Sparse ConvNets

Historically, the pursuit of efficient inference has been one of the dri...
11/21/2019 ∙ by Erich Elsen, et al. ∙ 0 ∙ share

read it
High Fidelity Speech Synthesis with Adversarial Networks

Generative adversarial networks have seen rapid development in recent ye...
09/25/2019 ∙ by Mikołaj Bińkowski, et al. ∙ 0 ∙ share

read it
The Difficulty of Training Sparse Neural Networks

We investigate the difficulties of training sparse neural networks and m...
06/25/2019 ∙ by Utku Evci, et al. ∙ 5 ∙ share

read it
Non-Differentiable Supervised Learning with Evolution Strategies and Hybrid Methods

In this work we show that Evolution Strategies (ES) are a viable method ...
06/07/2019 ∙ by Karel Lenc, et al. ∙ 9 ∙ share

read it
The State of Sparsity in Deep Neural Networks

We rigorously evaluate three state-of-the-art techniques for inducing sp...
02/25/2019 ∙ by Trevor Gale, et al. ∙ 0 ∙ share

read it
Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset

Generating musical audio directly with neural networks is notoriously di...
10/29/2018 ∙ by Curtis Hawthorne, et al. ∙ 0 ∙ share

read it
Efficient Neural Audio Synthesis

Sequential models achieve state-of-the-art results in audio, visual and ...
02/23/2018 ∙ by Nal Kalchbrenner, et al. ∙ 0 ∙ share

read it
Parallel WaveNet: Fast High-Fidelity Speech Synthesis

The recently-developed WaveNet architecture is the current state of the ...
11/28/2017 ∙ by Aaron van den Oord, et al. ∙ 0 ∙ share

read it
Onsets and Frames: Dual-Objective Piano Transcription

We consider the problem of transcribing polyphonic piano music with an e...
10/30/2017 ∙ by Curtis Hawthorne, et al. ∙ 0 ∙ share

read it
Mixed Precision Training

Deep neural networks have enabled progress in a wide variety of applicat...
10/10/2017 ∙ by Paulius Micikevicius, et al. ∙ 0 ∙ share

read it
Exploring Sparsity in Recurrent Neural Networks

Recurrent Neural Networks (RNN) are widely used to solve a variety of pr...
04/17/2017 ∙ by Sharan Narang, et al. ∙ 0 ∙ share

read it
DSD: Dense-Sparse-Dense Training for Deep Neural Networks

Modern deep neural networks have a large number of parameters, making th...
07/15/2016 ∙ by Song Han, et al. ∙ 0 ∙ share

read it
Deep Speech 2: End-to-End Speech Recognition in English and Mandarin

We show that an end-to-end deep learning approach can be used to recogni...
12/08/2015 ∙ by Dario Amodei, et al. ∙ 0 ∙ share

read it
Deep Speech: Scaling up end-to-end speech recognition

We present a state-of-the-art speech recognition system developed using ...
12/17/2014 ∙ by Awni Hannun, et al. ∙ 0 ∙ share

read it

Erich Elsen

Featured Co-authors

Oriol Vinyals

Hao Wu

Yi Wang

Song Han

Karen Simonyan

Koray Kavukcuoglu

Andrew Y. Ng

Chong Wang

Bryan Catanzaro

Matei Zaharia

Aaron van den Oord

On the Generalization Benefit of Noise in Stochastic Gradient Descent

Sparse GPU Kernels for Deep Learning

AlgebraNets

A Practical Sparse Approximation for Real Time Recurrent Learning

End-to-End Adversarial Text-to-Speech

Rigging the Lottery: Making All Tickets Winners

Fast Sparse ConvNets

High Fidelity Speech Synthesis with Adversarial Networks

The Difficulty of Training Sparse Neural Networks

Non-Differentiable Supervised Learning with Evolution Strategies and Hybrid Methods

The State of Sparsity in Deep Neural Networks

Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset

Efficient Neural Audio Synthesis

Parallel WaveNet: Fast High-Fidelity Speech Synthesis

Onsets and Frames: Dual-Objective Piano Transcription

Mixed Precision Training

Exploring Sparsity in Recurrent Neural Networks

DSD: Dense-Sparse-Dense Training for Deep Neural Networks

Deep Speech 2: End-to-End Speech Recognition in English and Mandarin

Deep Speech: Scaling up end-to-end speech recognition