13 citations · 25 across the 11 of their papers we have counts for
Showing 2022Show all
3 papers · 1 filter
cs.LG2022★ 1 cited
Look-ups are not (yet) all you need for deep learning inference
Calvin McCarter, Nicholas Dronen
Fast approximations to matrix multiplication have the potential to dramatically reduce the cost of neural network inference. Recent work on approximate matrix multiplication propos…
cs.LG2022★ 6 cited
Adaptive Block Floating-Point for Analog Deep Learning Hardware
Ayon Basumallik, Darius Bunandar, Nicholas Dronen +6
Analog mixed-signal (AMS) devices promise faster, more energy-efficient deep neural network (DNN) inference than their digital counterparts. However, recent studies show that DNNs…
stat.ML2022
Towards Backwards-Compatible Data with Confounded Domain Adaptation
Calvin McCarter
Most current domain adaptation methods address either covariate shift or label shift, but are not applicable where they occur simultaneously and are confounded with each other. Dom…