← Search

George E. Dahl

3 accepted papers

2025

Accelerating neural network training: An analysis of the AlgoPerf competition

ICLR 2025poster

The goal of the AlgoPerf: Training Algorithms competition is to evaluate practical speed-ups in neural network training achieved solely by improving the underlying training algorithms. In the external tuning ruleset, submissions must provide workload-agnostic hyperparameter search spaces, while in t…

Cited by 0SourcePDFScholar
2018

Large scale distributed neural network training through online distillation

ICLR 2018poster

Techniques such as ensembling and distillation promise model quality improvements when paired with almost any base model. However, due to increased test-time cost (for ensembles) and increased complexity of the training pipeline (for distillation), these techniques are challenging to use in industri…

Cited by 535SourcePDFScholar
2017

Neural Message Passing for Quantum Chemistry

ICML 2017poster

Supervised learning on molecules has incredible potential to be useful in chemistry, drug discovery, and materials science. Luckily, several promising and closely related neural network models invariant to molecular symmetries have already been described in the literature. These models learn a messa…