On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “HDC”

Laplace-HDC: Understanding the geometry of binary hyperdimensional computingcs.LG

Paper introduces Laplace-HDC for better binary hyperdimensional computing.

problem Improving binary hyperdimensional computing for spatial information.

method Develops Laplace-HDC using the Laplace kernel and Haar convolutional features.

result Laplace-HDC outperforms previous methods in encoding spatial information.

hyperdimensional computing binary vectors Laplace kernel Haar convolutional features image encoding

2024-04-16abs ↗pdf ↗

Graph Embeddings via Tensor Products and Approximately Orthonormal Codescs.SI

Proposes a new graph representation method using tensor products.

problem Dynamic graph representation and theoretical properties.

method Bind-and-sum approach in hyperdimensional computing (HDC), tensor product as binding operation.

result Memory vs. size analysis of graph representation size scaling.

graph embeddings tensor products hyperdimensional computing HDC adjacency matrices

2022-08-18abs ↗pdf ↗

ConformalHDC: Uncertainty-Aware Hyperdimensional Computing with Application to Neural Decodingstat.ML

ConformalHDC improves HDC's uncertainty quantification for neuromorphic learning.

problem Lack of rigorous uncertainty quantification in Hyperdimensional Computing.

method Combines conformal prediction with HDC's efficiency, proposing set-valued and point-valued formulations.

result Demonstrates improved robustness and accuracy in decoding neural stimulus information.

Hyperdimensional Computing Uncertainty Quantification Neuromorphic Learning Conformal Prediction Neural Decoding

2026-02-24abs ↗pdf ↗

G-Net: A Provably Easy Construction of High-Accuracy Random Binary Neural Networkscs.LG

G-Net constructs binary neural networks with high accuracy using randomized binary embeddings.

problem Creating high-accuracy binary neural networks with theoretical guarantees.

method Proposes a novel floating-point G-Net family with randomized binary embeddings and theoretical accuracy guarantees.

result Empirically, G-Net achieves almost 30% higher accuracy on CIFAR-10 compared to prior HDC models.

binary neural networks randomized algorithms hyperdimensional computing concentration of measure CIFAR-10

2025-11-26abs ↗pdf ↗

Tensor Products and Hyperdimensional Computingstat.ML

Explores tensor products in hyperdimensional computing.

problem Understanding tensor products in hyperdimensional computing.

method Generalized results from graph embeddings to vector symbolic architectures and hyperdimensional computing.

result Tensor product is the most general and expressive representation with errorless unbinding and detection.

Tensor Products Hyperdimensional Computing Vector Symbolic Architectures Graph Embeddings Orthogonality

2023-05-17abs ↗pdf ↗

Embedding Compression with Isotropic Iterative Quantizationcs.CL

Paper proposes IIQ for compressing embedding vectors.

problem Memory issues in representing large vocabularies.

method Isotropic iterative quantization (IIQ) for binary compression.

result More than 30x compression ratio with comparable performance.

embedding compression binary quantization deep learning NLP memory efficiency

2020-01-11abs ↗pdf ↗