arXiv:2311.11091 · v4

Deep Tensor Network

深度张量网络

首次提交 2023-11-18 22:41

版本更新 2026-11-10 01:26

雷达观测 2026-11-10 15:22

摘要

The Deep Tensor Network is a family of sequence operators built from contractions of queries, keys, and values. Tensor Attention mixes tokens through the Gram operators $Q(K^\top K)Q^\top$ and $K(Q^\top Q)K^\top$; Tensor Interaction mixes channels through operators derived from $C=Q^\top K$. Associativity lets us evaluate these products exactly without forming $n\times n$ token matrices. For query/key width $d$ and value width $d_v$, the Gram constructions use $O(d^2+dd_v)$ work and summary state per causal token, or $O(d^2)$ when $d_v=O(d)$. We derive prefix recurrences and distinguish trace, diagonal, and row normalization, including the conditions under which the weights are nonnegative and row-stochastic. The unmasked token operators are positive semidefinite with rank at most $d$, but their entries can be negative. We also give exact evaluations and costs for Hadamard and matrix-exponential variants.