D
Demjan Grubic
Publications - 6
Citations - 1210
Demjan Grubic is an academic researcher. The author has contributed to research in topics: Heuristics & Stochastic gradient descent. The author has an hindex of 5, co-authored 6 publications receiving 826 citations.
Papers
More filters
Proceedings Article
QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding
TL;DR: Quantized SGD (QSGD) as discussed by the authors is a family of compression schemes for gradient updates which provides convergence guarantees for convex and nonconvex objectives, under asynchrony, and can be extended to stochastic variance-reduced techniques.
Posted Content
QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding
TL;DR: Quantized SGD is proposed, a family of compression schemes for gradient updates which provides convergence guarantees and leads to significant reductions in end-to-end training time, and can be extended to stochastic variance-reduced techniques.
Proceedings ArticleDOI
Synchronous Multi-GPU Deep Learning with Low-Precision Communication: An Experimental Study
TL;DR: This paper conducts an empirical study to answer the question: can low-precision communication consistently improve the end-to-end performance of training modern neural networks, with no accuracy loss?
Proceedings Article
Communication-Efficient Stochastic Gradient Descent, with Applications to Neural Networks
TL;DR: Quantized SGD is proposed, a family of compression schemes for gradient updates which provides convergence guarantees and leads to significant reductions in end-to-end training time, and can be extended to stochastic variance-reduced techniques.