Phase-Associative Memory: Sequence Modeling in Complex Hilbert Space

📅 2026-04-06
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
Traditional vector-based associative memory models suffer from capacity degradation scaling as O(1/√n) due to superposition interference, limiting their ability to model long sequences. This work proposes Phase-Associative Memory (PAM), which represents states as complex-valued vectors in a complex Hilbert space, stores associations via outer products into matrix states, and retrieves them using conjugate inner products. PAM is the first method to natively integrate complex-valued hyperdimensional representations and conjugation operations into sequence modeling, fundamentally mitigating capacity decay. Under standard training protocols, PAM achieves a validation perplexity of 30.0 on WikiText-103 with approximately 100 million parameters—approaching the 27.1 attained by a same-scale Transformer—despite incurring roughly four times the arithmetic cost due to complex-number operations.

Technology Category

Application Category

📝 Abstract
We present Phase-Associative Memory (PAM), a recurrent sequence model in which all representations are complex-valued, associations accumulate in a matrix state $S_{t}$ $\in$ $\mathbb{C}^{d \times d}$ via outer products, and retrieval operates through the conjugate inner product $K_t^* \cdot Q_t / \sqrt{d}$. At $\sim$100M parameters on WikiText-103, PAM reaches validation perplexity 30.0, within $\sim$10\% of a matched transformer (27.1) trained under identical conditions, despite $4\times$ arithmetic overhead from complex computation and no custom kernels. We trace the experimental path from vector-state models, where holographic binding fails due to the $O(1/\sqrt{n})$ capacity degradation of superposed associations, to the matrix state that resolves it. The competitiveness of an architecture whose native operations are complex-valued superposition and conjugate retrieval is consistent with recent empirical evidence that semantic interpretation in both humans and large language models exhibits non-classical contextuality, and we discuss what this implies for the choice of computational formalism in language modeling.
Problem

Research questions and friction points this paper is trying to address.

sequence modeling
associative memory
complex Hilbert space
capacity degradation
contextuality
Innovation

Methods, ideas, or system contributions that make the work stand out.

Phase-Associative Memory
complex-valued representations
matrix-state associative memory
conjugate retrieval
holographic binding
🔎 Similar Papers
2024-05-10arXiv.orgCitations: 2
G
Gowrav Vishwakarma
Xavoc Technocrats Pvt. Ltd., https://xavoc.com, India
C
Christopher J. Agostino
NPC Worldwide, Bloomington, Indiana 47403, USA