Collage Inference: Achieving low tail latency during distributed image classification using coded redundancy models

no code implementations • 5 Jun 2019 • Krishna Narra, Zhifeng Lin, Ganesh Ananthanarayanan, Salman Avestimehr, Murali Annavaram

In this work, we argue that MLaaS platforms also provide unique opportunities to cut the cost of redundancy.

BIG-bench Machine Learning General Classification +1

GradiVeQ: Vector Quantization for Bandwidth-Efficient Gradient Aggregation in Distributed CNN Training

no code implementations • NeurIPS 2018 • Mingchao Yu, Zhifeng Lin, Krishna Narra, Songze Li, Youjie Li, Nam Sung Kim, Alexander Schwing, Murali Annavaram, Salman Avestimehr

Data parallelism can boost the training speed of convolutional neural networks (CNN), but could suffer from significant communication costs caused by gradient aggregation.

Dimensionality Reduction Quantization