Abstract
We present a novel global compression framework for deep neural networks that
automatically analyzes each layer to identify the optimal per-layer compression
ratio, while simultaneously achieving the desired overall compression. Our algorithm hinges on the idea of compressing each convolutional (or fully-connected) layer by slicing its channels into multiple groups and decomposing each group via low-rank decomposition. At the core of our algorithm is the derivation of layer-wise error bounds from the Eckart–Young–Mirsky theorem. We then leverage these bounds to frame the compression problem as an optimization problem where we wish to minimize the maximum compression error across layers and propose an efficient algorithm towards a solution. Our experiments indicate that our method outperforms existing low-rank compression approaches across a wide range of networks and data sets. We believe that our results open up new avenues for future research into the global performance-size trade-offs of modern neural networks.
automatically analyzes each layer to identify the optimal per-layer compression
ratio, while simultaneously achieving the desired overall compression. Our algorithm hinges on the idea of compressing each convolutional (or fully-connected) layer by slicing its channels into multiple groups and decomposing each group via low-rank decomposition. At the core of our algorithm is the derivation of layer-wise error bounds from the Eckart–Young–Mirsky theorem. We then leverage these bounds to frame the compression problem as an optimization problem where we wish to minimize the maximum compression error across layers and propose an efficient algorithm towards a solution. Our experiments indicate that our method outperforms existing low-rank compression approaches across a wide range of networks and data sets. We believe that our results open up new avenues for future research into the global performance-size trade-offs of modern neural networks.
| Original language | English |
|---|---|
| Title of host publication | Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021 |
| Editors | Marc'Aurelio Ranzato, Alina Beygelzimer, Yann Dauphin, Percy S. Liang, Jenn Wortman Vaughan |
| Publisher | Neural information processing systems foundation |
| Pages | 5328-5344 |
| Number of pages | 17 |
| ISBN (Electronic) | 9781713845393 |
| State | Published - 2021 |
| Event | 35th Conference on Neural Information Processing Systems, NeurIPS 2021 - Virtual, Online Duration: 6 Dec 2021 → 14 Dec 2021 |
Publication series
| Name | Advances in Neural Information Processing Systems |
|---|---|
| Volume | 7 |
| ISSN (Print) | 1049-5258 |
Conference
| Conference | 35th Conference on Neural Information Processing Systems, NeurIPS 2021 |
|---|---|
| City | Virtual, Online |
| Period | 6/12/21 → 14/12/21 |
Bibliographical note
Funding Information:This research was sponsored by the United States Air Force Research Laboratory and the United States Air Force Artificial Intelligence Accelerator and was accomplished under Cooperative Agreement Number FA8750-19-2-1000. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the United States Air Force or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation herein. This work was further supported by the Office of Naval Research (ONR) Grant N00014-18-1-2830.
Funding Information:
Air Force Research Laboratory and the United States Air Force Artificial Intelligence Accelerator accomplished under Cooperative Agreement Number FA8750-19-2-1000 and the Office of Naval Research (ONR) Grant N00014-18-1-2830.
Publisher Copyright:
© 2021 Neural information processing systems foundation. All rights reserved.
ASJC Scopus subject areas
- Computer Networks and Communications
- Information Systems
- Signal Processing