activity
20152019
most citedBlocks and Fuel: Frameworks for deep learning

125 citations · 149 across the 4 of their papers we have counts for

collaborators

8 papers

stat.ML20193 cited

Fast Training of Sparse Graph Neural Networks on Dense Hardware

Matej Balog, Bart van Merriënboer, Subhodeep Moitra +2

Graph neural networks have become increasingly popular in recent years due to their ability to naturally encode relational input data and their ability to scale to large graphs by…

cs.LG2019

On the interplay between noise and curvature and its effect on optimization and generalization

Valentin Thomas, Fabian Pedregosa, Bart van Merriënboer +3

The speed at which one can minimize an expected loss using stochastic methods depends on two properties: the curvature of the loss and the variance of the gradients. While most pre…

cs.LG2018

Automatic differentiation in ML: Where we are and where we should be going

Bart van Merriënboer, Olivier Breuleux, Arnaud Bergeron +1

We review the current state of automatic differentiation (AD) for array programming in machine learning (ML), including the different approaches such as operator overloading (OO) a…

cs.LG2018

Tangent: Automatic differentiation using source-code transformation for dynamically typed array programming

Bart van Merriënboer, Dan Moldovan, Alexander B Wiltschko

The need to efficiently calculate first- and higher-order derivatives of increasingly complex models expressed in Python has stressed or exceeded the capabilities of available tool…

cs.MS201714 cited

Tangent: Automatic Differentiation Using Source Code Transformation in Python

Bart van Merriënboer, Alexander B. Wiltschko, Dan Moldovan

Automatic differentiation (AD) is an essential primitive for machine learning programming systems. Tangent is a new library that performs AD using source code transformation (SCT)…

stat.ML20177 cited

Multiscale sequence modeling with a learned dictionary

Bart van Merriënboer, Amartya Sanyal, Hugo Larochelle +1

We propose a generalization of neural network sequence models. Instead of predicting one symbol at a time, our multi-scale model makes predictions over multiple, potentially overla…