We present a provable, sampling-based approach for generating compact Convolutional Neural Networks (CNNs) by identifying and removing redundant filters from an over-parameterized network. Our algorithm uses a small batch of input data points to assign a saliency score to each filter and constructs an importance sampling distribution where filters that highly affect the output are sampled with correspondingly high probability. In contrast to existing filter pruning approaches, our method is simultaneously data-informed, exhibits provable guarantees on the size and performance of the pruned network, and is widely applicable to varying network architectures and data sets. Our analytical bounds bridge the notions of compressibility and importance of network structures, which gives rise to a fully-automated procedure for identifying and preserving filters in layers that are essential to the network's performance. Our experimental evaluations on popular architectures and data sets show that our algorithm consistently generates sparser and more efficient models than those constructed by existing filter pruning approaches.
|State||Published - 2020|
|Event||8th International Conference on Learning Representations, ICLR 2020 - Addis Ababa, Ethiopia|
Duration: 30 Apr 2020 → …
|Conference||8th International Conference on Learning Representations, ICLR 2020|
|Period||30/04/20 → …|
Bibliographical noteFunding Information:
This research was supported in part by the U.S. National Science Foundation (NSF) under Awards 1723943 and 1526815, Office of Naval Research (ONR) Grant N00014-18-1-2830, Microsoft, and JP Morgan Chase.
© 2020 8th International Conference on Learning Representations, ICLR 2020. All rights reserved.
ASJC Scopus subject areas
- Linguistics and Language
- Language and Linguistics
- Computer Science Applications