Timezone: »

Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition
Lucas Liebenwein · Alaa Maalouf · Dan Feldman · Daniela Rus

Fri Dec 10 08:30 AM -- 10:00 AM (PST) @ Virtual

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.

Author Information

Lucas Liebenwein (Massachusetts Institute of Technology)
Alaa Maalouf (The University of Haifa)
Dan Feldman (University of Haifa)
Daniela Rus (Massachusetts Institute of Technology)

More from the Same Authors