Pruning Randomly Initialized Neural Networks with Iterative Randomization

Abstract

Pruning the weights of randomly initialized neural networks plays an important role in the context of lottery ticket hypothesis. Ramanujan et al. (2020) empirically showed that only pruning the weights can achieve remarkable performance instead of optimizing the weight values. However, to achieve the same level of performance as the weight optimization, the pruning approach requires more parameters in the networks before pruning and thus more memory space. To overcome this parameter inefficiency, we introduce a novel framework to prune randomly initialized neural networks with iteratively randomizing weight values (IteRand). Theoretically, we prove an approximation theorem in our framework, which indicates that the randomizing operations are provably effective to reduce the required number of the parameters. We also empirically demonstrate the parameter efficiency in multiple experiments on CIFAR-10 and ImageNet. The code is available at: https://github.com/dchiji-ntt/iterand

35th Conference on Neural Information Processing Systems (NeurIPS 2021); Selected for a spotlight presentation

References in corpus (6)

• DSD: Dense-Sparse-Dense Training for Deep Neural Networks
• Picking Winning Tickets Before Training by Preserving Gradient Flow
• Parameter Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterization
• Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask
• Proving the Lottery Ticket Hypothesis: Pruning is All You Need
• Multi-Prize Lottery Ticket Hypothesis: Finding Accurate Binary Neural Networks by Pruning A Randomly Weighted Network