We present a novel approach for training neural networks that leverages packed Shamir secret sharing scheme. For specific training protocols based on Shamir scheme, we demonstrate how to realize the conversion
Furthermore, we introduce what we call sparsely packed Shamir sharing which allows us to address the issue of network routing efficiently, and packed Beaver triples which is an extension of the widely used technique of Beaver triples for packed secret sharing (for dishonest majority).Goyal, Vipul...