Accelerating Deep Learning by Focusing on the Biggest Losers

10/02/2019
by   Angela H. Jiang, et al.
669

This paper introduces Selective-Backprop, a technique that accelerates the training of deep neural networks (DNNs) by prioritizing examples with high loss at each iteration. Selective-Backprop uses the output of a training example's forward pass to decide whether to use that example to compute gradients and update parameters, or to skip immediately to the next example. By reducing the number of computationally-expensive backpropagation steps performed, Selective-Backprop accelerates training. Evaluation on CIFAR10, CIFAR100, and SVHN, across a variety of modern image models, shows that Selective-Backprop converges to target error rates up to 3.5x faster than with standard SGD and between 1.02--1.8x faster than a state-of-the-art importance sampling approach. Further acceleration of 26 for selection, thus also skipping forward passes of low priority examples.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/16/2019

Selective sampling for accelerating training of deep neural networks

We present a selective sampling method designed to accelerate the traini...
research
06/18/2020

Accelerating Training in Artificial Neural Networks with Dynamic Mode Decomposition

Training of deep neural networks (DNNs) frequently involves optimizing s...
research
05/23/2017

Selective Classification for Deep Neural Networks

Selective classification techniques (also known as reject option) have n...
research
05/08/2019

AutoAssist: A Framework to Accelerate Training of Deep Neural Networks

Deep neural networks have yielded superior performance in many applicati...
research
03/09/2021

Selective and Features based Adversarial Example Detection

Security-sensitive applications that relay on Deep Neural Networks (DNNs...
research
02/24/2019

Rapidly Adapting Moment Estimation

Adaptive gradient methods such as Adam have been shown to be very effect...
research
07/16/2021

When does loss-based prioritization fail?

Not all examples are created equal, but standard deep neural network tra...

Please sign up or login with your details

Forgot password? Click here to reset