Efficient Lottery Ticket Finding: Less Data is More

by   Zhenyu Zhang, et al.

The lottery ticket hypothesis (LTH) reveals the existence of winning tickets (sparse but critical subnetworks) for dense networks, that can be trained in isolation from random initialization to match the latter's accuracies. However, finding winning tickets requires burdensome computations in the train-prune-retrain process, especially on large-scale datasets (e.g., ImageNet), restricting their practical benefits. This paper explores a new perspective on finding lottery tickets more efficiently, by doing so only with a specially selected subset of data, called Pruning-Aware Critical set (PrAC set), rather than using the full training set. The concept of PrAC set was inspired by the recent observation, that deep networks have samples that are either hard to memorize during training, or easy to forget during pruning. A PrAC set is thus hypothesized to capture those most challenging and informative examples for the dense model. We observe that a high-quality winning ticket can be found with training and pruning the dense network on the very compact PrAC set, which can substantially save training iterations for the ticket finding process. Extensive experiments validate our proposal across diverse datasets and network architectures. Specifically, on CIFAR-10, CIFAR-100, and Tiny ImageNet, we locate effective PrAC sets at 35.32 sizes. On top of them, we can obtain the same competitive winning tickets for the corresponding dense networks, yet saving up to 82.85 63.54 we show that a PrAC set found is reusable across different network architectures, which can amortize the extra cost of finding PrAC sets, yielding a practical regime for efficient lottery ticket finding.



There are no comments yet.


page 8

page 14


Good Students Play Big Lottery Better

Lottery ticket hypothesis suggests that a dense neural network contains ...

The Elastic Lottery Ticket Hypothesis

Lottery Ticket Hypothesis raises keen attention to identifying sparse tr...

Provably Efficient Lottery Ticket Discovery

The lottery ticket hypothesis (LTH) claims that randomly-initialized, de...

Drawing early-bird tickets: Towards more efficient training of deep networks

(Frankle & Carbin, 2019) shows that there exist winning tickets (small b...

Growing Efficient Deep Networks by Structured Continuous Sparsification

We develop an approach to training deep networks while dynamically adjus...

Picking Winning Tickets Before Training by Preserving Gradient Flow

Overparameterization has been shown to benefit both the optimization and...

Energy-Aware Neural Architecture Optimization with Fast Splitting Steepest Descent

Designing energy-efficient networks is of critical importance for enabli...

Code Repositories


[ICML 2021] "Efficient Lottery Ticket Finding: Less Data is More" by Zhenyu Zhang*, Xuxi Chen*, Tianlong Chen*, Zhangyang Wang

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.