Change the Product, Keep the Parameters: Associative Algebra Layers for Transformers
Algebraic Transformer layers raise small-model generation throughput 6.2-7.8% but lower downstream scores.
Stories per day · 30 days
1 RSS
2 stories, newest first · one card per story
Stories tagged #matrix-multiplication
Low-Rank Masking for Single-Server Matrix Multiplication
Researchers prove rank-r additive masks for outsourced matrix multiplication achieve maximal-correlation secrecy of at most q^-r, with a matching lower bound.