← Search

Peter Hawkins

2 accepted papers

2021

Rethinking Attention with Performers

ICLR 2021oral

We introduce Performers, Transformer architectures which can estimate regular (softmax) full-rank-attention Transformers with provable accuracy, but using only linear (as opposed to quadratic) space and time complexity, without relying on any priors such as sparsity or low-rankness. To approximate s…

2018

Mesh-TensorFlow: Deep Learning for Supercomputers

NeurIPS 2018poster

Batch-splitting (data-parallelism) is the dominant distributed Deep Neural Network (DNN) training strategy, due to its universal applicability and its amenability to Single-Program-Multiple-Data (SPMD) programming. However, batch-splitting suffers from problems including the inability to train very…