HyperSpace: A Generalized Framework for Spatial Encoding in Hyperdimensional Representations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Snyder, Shay, Capodieci, Andrew, Gorsich, David, Parsa, Maryam
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915994738360320
author Snyder, Shay
Capodieci, Andrew
Gorsich, David
Parsa, Maryam
author_facet Snyder, Shay
Capodieci, Andrew
Gorsich, David
Parsa, Maryam
contents Vector Symbolic Architectures (VSAs) provide a well-defined algebraic framework for compositional representations in hyperdimensional spaces. We introduce HyperSpace, an open-source framework that decomposes VSA systems into modular operators for encoding, binding, bundling, similarity, cleanup, and regression. Using HyperSpace, we analyze and benchmark two representative VSA backends: Holographic Reduced Representations (HRR) and Fourier Holographic Reduced Representations (FHRR). Although FHRR provides lower theoretical complexity for individual operations, HyperSpaces modularity reveals that similarity and cleanup dominate runtime in spatial domains. As a result, HRR and FHRR exhibit comparable end-to-end performance. Differences in memory footprint introduce additional deployment trade-offs where HRR requires approximately half the memory of FHRR vectors. By enabling modular, system-level evaluation, HyperSpace reveals practical trade-offs in VSA pipelines that are not apparent from theoretical or operator-level comparisons alone.
format Preprint
id arxiv_https___arxiv_org_abs_2604_15113
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle HyperSpace: A Generalized Framework for Spatial Encoding in Hyperdimensional Representations
Snyder, Shay
Capodieci, Andrew
Gorsich, David
Parsa, Maryam
Artificial Intelligence
Vector Symbolic Architectures (VSAs) provide a well-defined algebraic framework for compositional representations in hyperdimensional spaces. We introduce HyperSpace, an open-source framework that decomposes VSA systems into modular operators for encoding, binding, bundling, similarity, cleanup, and regression. Using HyperSpace, we analyze and benchmark two representative VSA backends: Holographic Reduced Representations (HRR) and Fourier Holographic Reduced Representations (FHRR). Although FHRR provides lower theoretical complexity for individual operations, HyperSpaces modularity reveals that similarity and cleanup dominate runtime in spatial domains. As a result, HRR and FHRR exhibit comparable end-to-end performance. Differences in memory footprint introduce additional deployment trade-offs where HRR requires approximately half the memory of FHRR vectors. By enabling modular, system-level evaluation, HyperSpace reveals practical trade-offs in VSA pipelines that are not apparent from theoretical or operator-level comparisons alone.
title HyperSpace: A Generalized Framework for Spatial Encoding in Hyperdimensional Representations
topic Artificial Intelligence
url https://arxiv.org/abs/2604.15113