"Making Models Shallow Again: Jointly Learning to Reduce Non-Linearity and Depth for Latency-Efficient Private Inference"

Cat: cs LG

Link: arxiv.org/pdf/2304.13274v1 (https://arxiv.org/pdf/2304.13274v1)

https://nitter.moomoo.me/ArXivGPT/status/1651760893884252160#m