Multirate Training of Neural Networks

Abstract

We propose multirate training of neural networks: partitioning neural network parameters into "fast" and "slow" parts which are trained on different time scales, where slow parts are updated less frequently. By choosing appropriate partitionings we can obtain substantial computational speed-up for transfer learning tasks. We show for applications in vision and NLP that we can fine-tune deep neural networks in almost half the time, without reducing the generalization performance of the resulting models. We analyze the convergence properties of our multirate scheme and draw a comparison with vanilla SGD. We also discuss splitting choices for the neural network parameters which could enhance generalization performance when neural networks are trained from scratch. A multirate approach can be used to learn different features present in the data and as a form of regularization. Our paper unlocks the potential of using multirate techniques for neural network training and provides several starting points for future work in this area.

Appeared in ICML 2022 (errata added on 19 Oct., 2022)

References in corpus (6)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Large Batch Training of Convolutional Networks
• What makes ImageNet good for transfer learning?
• Using Fast Weights to Attend to the Recent Past
• Rethinking the Usage of Batch Normalization and Dropout in the Training of Deep Neural Networks
• Visualizing and Understanding the Effectiveness of BERT