Tag
Introduces (MPO)², a framework combining learned matrix product operator feature embeddings with compact polynomial weight tensors for efficient multivariate polynomial optimization, achieving improved performance over existing tensor decomposition based polynomial models.
An Arxiv AI paper on polynomial approximation of activation functions ends with the author's wish to marry his high school sweetheart, highlighting a personal touch in Chinese tech academia.
SHiPPO extends HiPPO by transporting polynomial projection coefficients into a moving channel frame, enabling selective state-space models to recover order-sensitive memory signals. The paper provides theoretical foundations and diagnostics supporting its transported-memory prior.