Timezone: »

Structured Transforms for Small-Footprint Deep Learning
Vikas Sindhwani · Tara Sainath · Sanjiv Kumar

Wed Dec 09 04:00 PM -- 08:59 PM (PST) @ 210 C #34

We consider the task of building compact deep learning pipelines suitable for deploymenton storage and power constrained mobile devices. We propose a uni-fied framework to learn a broad family of structured parameter matrices that arecharacterized by the notion of low displacement rank. Our structured transformsadmit fast function and gradient evaluation, and span a rich range of parametersharing configurations whose statistical modeling capacity can be explicitly tunedalong a continuum from structured to unstructured. Experimental results showthat these transforms can significantly accelerate inference and forward/backwardpasses during training, and offer superior accuracy-compactness-speed tradeoffsin comparison to a number of existing techniques. In keyword spotting applicationsin mobile speech recognition, our methods are much more effective thanstandard linear low-rank bottleneck layers and nearly retain the performance ofstate of the art models, while providing more than 3.5-fold compression.

Author Information

Vikas Sindhwani (Google)
Tara Sainath (Google)
Sanjiv Kumar (Google)

More from the Same Authors