Andrew Geng, Pin-Yu Chen
IEEE SaTML 2024
Homomorphic encryption enables private artificial intelligence computations to be run on the cloud. Recent work used tile tensors to speed up the evaluation of neural network inference. We introduce an extension to tile tensors for the complex plane, resulting in an ∼ 1.68 × amortized speedup.
Andrew Geng, Pin-Yu Chen
IEEE SaTML 2024
Raphaël Pestourie, Youssef Mroueh, et al.
npj Computational Materials
Hiroki Yanagisawa, Kohei Miyaguchi, et al.
NeurIPS 2022
Aditya Kashyap, Maria Anna Rapsomaniki, et al.
TIBTECH