DegreeSpar: Structured Degree Sparsity for Efficient Secure Transformer Inference
DegreeSpar is introduced, which formulates secure Transformer compression as structured sparsification over nonlinear polynomial degrees, establishing structured polynomial degree as an effective shared optimization space for secure Transformer compression.
Yi-Fei Cai, Zhuo-Ran Li, Xiao-Zuo Shen et al.
· 0 citations