Róbert Ormándi

Large scale distributed neural network training through online\n distillation

2018 · arXiv (Cornell University)

Techniques such as ensembling and distillation promise model quality\nimprovements when paired with almost any base model. However, due to increased\ntest-time cost (for ensembles) and increased complexity of the training\npipeline (for distillation), these techniques are challenging …