Approximating the weight gradient for a subset of layers and batches yields 3.5% to 7% wall-clock training speedup on CIFAR-10 deep CNNs with minimal validation accuracy loss.
Faster Neural Network Training with Approximate Tensor Operations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We propose a novel technique for faster deep neural network training which systematically applies sample-based approximation to the constituent tensor operations, i.e., matrix multiplications and convolutions. We introduce new sampling techniques, study their theoretical properties, and prove that they provide the same convergence guarantees when applied to SGD training. We apply approximate tensor operations to single and multi-node training of MLP and CNN networks on MNIST, CIFAR-10 and ImageNet datasets. We demonstrate up to 66% reduction in the amount of computations and communication, and up to 1.37x faster training time while maintaining negligible or no impact on the final test accuracy.
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Accelerated CNN Training Through Gradient Approximation
Approximating the weight gradient for a subset of layers and batches yields 3.5% to 7% wall-clock training speedup on CIFAR-10 deep CNNs with minimal validation accuracy loss.