Timezone: »

 
Poster
Demystifying and Generalizing BinaryConnect
Tim Dockhorn · Yaoliang Yu · Eyyüb Sari · Mahdi Zolnouri · Vahid Partovi Nia

Wed Dec 08 04:30 PM -- 06:00 PM (PST) @
in Poster Session 4 »

BinaryConnect (BC) and its many variations have become the de facto standard for neural network quantization. However, our understanding of the inner workings of BC is still quite limited. We attempt to close this gap in four different aspects: (a) we show that existing quantization algorithms, including post-training quantization, are surprisingly similar to each other; (b) we argue for proximal maps as a natural family of quantizers that is both easy to design and analyze; (c) we refine the observation that BC is a special case of dual averaging, which itself is a special case of the generalized conditional gradient algorithm; (d) consequently, we propose ProxConnect (PC) as a generalization of BC and we prove its convergence properties by exploiting the established connections. We conduct experiments on CIFAR-10 and ImageNet, and verify that PC achieves competitive performance.

Keywords: Deep Learning

Author Information

Tim Dockhorn (University of Waterloo)
Yaoliang Yu (Carnegie Mellon University)
Eyyüb Sari (Huawei Noah's Ark Lab)
Mahdi Zolnouri (Huawei)
Vahid Partovi Nia (Huawei Noah's Ark Lab)

More from the Same Authors