Michael Schaarschmidt | DeepAI

AI Chat

Featured Co-authors

Yee Whye Teh
122 publications
Razvan Pascanu
87 publications
Petar Veličković
59 publications
Peter Battaglia
33 publications
Alvaro Sanchez-Gonzalez
20 publications
James Martens
16 publications
Morgane Riviere
16 publications
Peter W. Battaglia
15 publications
Hyunjik Kim
15 publications
Alexander Kuhnle
15 publications
Adam Paszke
13 publications

∙ 10/07/2022

Automatic Discovery of Composite SPMD Partitioning Strategies in PartIR

Large neural network models are commonly trained through a combination o...

0 Sami Alabed, et al. ∙

∙ 09/26/2022

Learned Force Fields Are Ready For Ground State Catalyst Discovery

We present evidence that learned density functional theory (“DFT”) force...

0 Michael Schaarschmidt, et al. ∙

∙ 05/31/2022

Pre-training via Denoising for Molecular Property Prediction

Many important problems involving molecular property prediction from 3D ...

0 Sheheryar Zaidi, et al. ∙

∙ 12/06/2021

Automap: Towards Ergonomic Automated Parallelism for ML Models

The rapid rise in demand for training large neural network architectures...

8 Michael Schaarschmidt, et al. ∙

∙ 06/15/2021

Very Deep Graph Neural Networks Via Noise Regularisation

Graph Neural Networks (GNNs) perform learned message passing over an inp...

0 Jonathan Godwin, et al. ∙

∙ 09/16/2019

Learning Index Selection with Structured Action Spaces

Configuration spaces for computer systems can be challenging for traditi...

0 Jeremy Welborn, et al. ∙

∙ 09/15/2019

Wield: Systematic Reinforcement Learning With Progressive Randomization

Reinforcement learning frameworks have introduced abstractions to implem...

0 Michael Schaarschmidt, et al. ∙

∙ 10/21/2018

RLgraph: Flexible Computation Graphs for Deep Reinforcement Learning

Reinforcement learning (RL) tasks are challenging to implement, execute ...

0 Michael Schaarschmidt, et al. ∙

∙ 08/23/2018

LIFT: Reinforcement Learning in Computer Systems by Learning From Demonstrations

Reinforcement learning approaches have long appealed to the data managem...

0 Michael Schaarschmidt, et al. ∙

Are you a researcher?
Expose your work
to one of the largest
A.I. communities in the world