# Hypervector Design for Efficient Hyperdimensional Computing on Edge Devices

arXiv: https://arxiv.org/abs/2103.06709 · HTML: https://mlsanity.com/paper/2103.06709/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 35 references that are in the map.
- First posted on arXiv 8 Mar 2021.

## Builds on (most cited first, 6 of 6)

- [Convergence of Edge Computing and Deep Learning: A Comprehensive Survey](https://mlsanity.com/paper/1907.08349/) (2019)
- [Classification using Hyperdimensional Computing: A Review](https://mlsanity.com/paper/2004.11204/) (2020)
- [FANN-on-MCU: An Open-Source Toolkit for Energy-Efficient Neural Network Inference at the Edge of the Internet of Things](https://mlsanity.com/paper/1911.03314/) (2019)
- [An Accurate EEGNet-based Motor-Imagery Brain-Computer Interface for Low-Power Edge Computing](https://mlsanity.com/paper/2004.00077/) (2020)
- [Exploring Embedding Methods in Binary Hyperdimensional Computing: A Case Study for Motor-Imagery based Brain-Computer Interfaces](https://mlsanity.com/paper/1812.05705/) (2018)
- [OpenHealth: Open Source Platform for Wearable Health Monitoring](https://mlsanity.com/paper/1903.03168/) (2019)

## Built on by (most cited first, 16 of 16)

- [A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part II: Applications, Cognitive Models, and Challenges](https://mlsanity.com/paper/2112.15424/) (2021)
- [Understanding Hyperdimensional Computing for Parallel Single-Pass Learning](https://mlsanity.com/paper/2202.04805/) (2022)
- [A Brain-Inspired Low-Dimensional Computing Classifier for Inference on Tiny Devices](https://mlsanity.com/paper/2203.04894/) (2022)
- [Learning from Hypervectors: A Survey on Hypervector Encoding](https://mlsanity.com/paper/2308.00685/) (2023)
- [Laplace-HDC: Understanding the geometry of binary hyperdimensional computing](https://mlsanity.com/paper/2404.10759/) (2024)
- [Automated Architecture Search for Brain-inspired Hyperdimensional Computing](https://mlsanity.com/paper/2202.05827/) (2022)
- [MetaLDC: Meta Learning of Low-Dimensional Computing Classifiers for Fast On-Device Adaption](https://mlsanity.com/paper/2302.12347/) (2023)
- [Training a HyperDimensional Computing Classifier using a Threshold on its Confidence](https://mlsanity.com/paper/2305.19007/) (2023)
- [MicroHD: An Accuracy-Driven Optimization of Hyperdimensional Computing Algorithms for TinyML systems](https://mlsanity.com/paper/2404.00039/) (2024)
- [Hyperdimensional computing: a fast, robust and interpretable paradigm for biological data](https://mlsanity.com/paper/2402.17572/) (2024)
- [tinyMAN: Lightweight Energy Manager using Reinforcement Learning for Energy Harvesting Wearable IoT Devices](https://mlsanity.com/paper/2202.09297/) (2022)
- [uHD: Unary Processing for Lightweight and Dynamic Hyperdimensional Computing](https://mlsanity.com/paper/2311.10778/) (2023)
- [THDC: Training Hyperdimensional Computing Models with Backpropagation](https://mlsanity.com/paper/2602.00116/) (2026)
- [Robust Clustering using Hyperdimensional Computing](https://mlsanity.com/paper/2312.02407/) (2023)
- [ScalableHD: Scalable and High-Throughput Hyperdimensional Computing Inference on Multi-Core CPUs](https://mlsanity.com/paper/2506.09282/) (2025)
- [Primitive-Driven Acceleration of Hyperdimensional Computing for Real-Time Image Classification](https://mlsanity.com/paper/2601.20061/) (2026)

## Abstract (arXiv)

Hyperdimensional computing (HDC) has emerged as a new light-weight learning algorithm with smaller computation and energy requirements compared to conventional techniques. In HDC, data points are represented by high-dimensional vectors (hypervectors), which are mapped to high-dimensional space (hyperspace). Typically, a large hypervector dimension (≥1000) is required to achieve accuracies comparable to conventional alternatives. However, unnecessarily large hypervectors increase hardware and energy costs, which can undermine their benefits. This paper presents a technique to minimize the hypervector dimension while maintaining the accuracy and improving the robustness of the classifier. To this end, we formulate the hypervector design as a multi-objective optimization problem for the first time in the literature. The proposed approach decreases the hypervector dimension by more than 32× while maintaining or increasing the accuracy achieved by conventional HDC. Experiments on a commercial hardware platform show that the proposed approach achieves more than one order of magnitude reduction in model size, inference time, and energy consumption. We also demonstrate the trade-off between accuracy and robustness to noise and provide Pareto front solutions as a design parameter in our hypervector design.