Hyperdimensional Computing

Follow this topic Ask about this topic

Momentum

2 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 24

All topics

Phase-HDC: Replacing Optimizer History with Gradient Thresholds in Discrete Phase Learning
Oct 7, 2026Ahmed NebliMemory-Efficient Training Sign-Based Optimization
Mathalyse Research
Derandomizing Dense Binary Hypervector Codebooks for Quantized Scalars
Sep 29, 2026Dmitri Rachkovskij, Evgeny Osipov, Olexander Volkov +2Vector Quantization Hyperdimensional Computing
Department of Computer Science, Electrical and Space Engineering, Luleå University of Technology, 971 87 Luleå, Sweden · Institute of Information Technologies and Systems, 03187 Kyiv, Ukraine · AI, Robotics and Cybersecurity Center (ARC) and Department of Computer Science, Örebro University, 70182 Örebro, Sweden +2
Learning Holographic Reduced Representations with Clifford Variational Autoencoders
Sep 23, 2026Mohamed Malek Abid, P. Michael FurlongVariational Autoencoders Visual Representation Learning
Institute of Neuroinformatics, University of Zurich & ETH Zurich · National Research Council Canada & Centre for Theoretical Neuroscience, Systems Design Engineering, University of Waterloo, Waterloo, Canada
Bridging the Gap Between Hyperdimensional Computing and Kernel Methods via the Nyström Method
Aug 7, 2026Quanling Zhao, Anthony Hitchcock Thomas, Ari Brin +2Hyperdimensional Computing
Department of Computer Science and Engineering, UC San Diego
How to Build Marcus's Algebraic Mind: From Thagard's Brain--Mind Viewpoint
Jul 18, 2026Hiroyuki Chuma, Kanji Otsuka, Yoichi SatoComputational Cognitive Modeling Hyperdimensional Computing
Institute of Innovation Research, Hitotsubashi University (Professor Emeritus) · Meisei University (Professor Emeritus) · Shuhari System
Qubit-Efficient Quantum Search for Hyperdimensional Decomposition via Logarithmic Encoding
Jul 11, 2026Sanggeon Yun, Hyunwoo Oh, Ryozo Masukawa +2Hyperdimensional Computing
University of California, Irvine
Creating Intelligence: A Computational Foundation for AGI
Jun 30, 2026Peter OvermannComputational Cognitive Modeling Hyperdimensional Computing
Compiler-Driven Approximation Tuning for Hyperdimensional Computing
Jun 25, 2026Xavier Routh, Abdul Rafae Noor, Akash Kothari +4Hyperdimensional Computing Approximate Computing
University of Illinois Urbana-Champaign Urbana, IL, USA · University of California San Diego La Jolla, CA, USA
Holographic Memory for Zero-Shot Compositional Reasoning in Knowledge Graphs: A Mechanistic Study of Where and Why It Fails
Jun 23, 2026Randhir KumarCompositional Reasoning KG Embedding
Independent Researcher
QeHDC: Hyperdimensional Computing based on Quantum-enhanced binding and SuperClass Construction
Jun 21, 2026Yangjie Xu, Hui Huang, Li Ning +1Hybrid Quantum-Classical ML Hyperdimensional Computing
University of Luxembourg Kirchberg, Luxembourg · Stellaris AI Limited Hong Kong, China
Hyperdimensional computing for structured querying on tabular data embeddings
Jun 11, 2026Sebastián Bugedo, Stijn VansummerenHyperdimensional Computing
UHasselt, DSI Diepenbeek, Belgium
D2H-AD: A Hybrid Model Utilizing Hyperdimensional Computing for Advanced Anomaly Detection
Jun 11, 2026Ghazal Ghajari, Elaheh Ghajari, Ashutosh Ghimire +3Hyperdimensional Computing Anomaly Detection
Wright State University, Dayton, Ohio 45435, USA · Azad University, Ahvaz 6887561349, Iran · Stevens Institute of Technology, Hoboken, New Jersey 07030, USA +1
How to Build Marcus's Algebraic Mind: Algebro-Deterministic Substrate over Galois Fields
May 20, 2026Hiroyuki Chuma, Kanji Otsuk, Yoichi SatoComputational Cognitive Modeling Hyperdimensional Computing
Institute of Innovation Research, Hitotsubashi University, Kunitachi, Tokyo 186-8603, Japan (Professor Emeritus) · Meisei University, Hino, Tokyo, Japan (Professor Emeritus) · Shuhari System, Tokyo, Japan
Encoding Robust Topological Signatures for Hyperdimensional Computing
May 16, 2026Arpan KusariImage Corruption Robustness Hyperdimensional Computing
University of Michigan Transportation Research Institute University of Michigan Ann Arbor, MI 48109
Bridging Silicon and the Hippocampus: Algebro-Deterministic Memory "VaCoAl" as a Substrate for Vector-HaSH and TEM
May 15, 2026Hiroyuki Chuma, Kanji Otsuka, Yoichi SatoHyperdimensional Computing Associative Memory
Institute of Innovation Research, Hitotsubashi University, Kunitachi, Tokyo 186-8603, Japan · Meisei University, Hino, Tokyo, Japan · Shuhari System, Tokyo, Japan
Contextual Bandits for Resource-Constrained Devices using Probabilistic Learning
May 13, 2026Marco Angioli, Kevin Johansson, Antonello Rosato +2Hyperdimensional Computing Contextual Bandits
Sapienza University of Rome · Orebro University · Linkoping University +1
Graph-Structured Hyperdimensional Computing for Data-Efficient and Explainable Process-Structure-Property Prediction
May 8, 2026Jingzhan Ge, Ajeeth Vellore, Ajinkya Palwe +5Interpretable ML Materials Property Prediction
School of Mechanical, Aerospace, and Manufacturing Engineering, University of Connecticut, Storrs, CT 06269 USA · U.S. Army Combat Capabilities Development Command, Ground Vehicle Systems Center, Warren, MI 48397 USA
Task-Aware Scanning Parameter Configuration for Robotic Inspection Using Vision Language Embeddings and Hyperdimensional Computing
May 5, 2026Zhiling Chen, David Gorsich, Matthew P. Castanier +3Robotic Inspection Robotics
aSchool of Mechanical, Aerospace, and Manufacturing Engineering, University of Connecticut, Storrs, Connecticut, USA · bUS Army DEVCOM Ground Vehicle Systems Center, Warren, Michigan, USA
Hyper-Dimensional Fingerprints as Molecular Representations
Apr 30, 2026Jonas Teufel, Luca Torresi, André Eberhard +1Hyperdimensional Computing Molecular Property Prediction
Karlsruhe Institute of Technology (KIT), Institute of Nanotechnology (INT), Kaiserstraße 12, Karlsruhe, Germany. · Karlsruhe Institute of Technology (KIT), Institute of Anthropomatics and Robotics (IAR), Kaiserstraße 12, Karlsruhe, Germany.
ImageHD: Energy-Efficient On-Device Continual Learning of Visual Representations via Hyperdimensional Computing
Apr 23, 2026Jebacyril Arockiaraj, Dhruv Parikh, Viktor PrasannaVisual Representation Learning Energy-Efficient ML
University of Southern California, Los Angeles, CA, USA
SRMU: Relevance-Gated Updates for Streaming Hyperdimensional Memories
Apr 16, 2026Shay Snyder, Andrew Capodieci, David Gorsich +1Hyperdimensional Computing Vector Symbolic Architectures
George Mason University · George Mason University, USA · Neya Robotics +3
HyperSpace: A Generalized Framework for Spatial Encoding in Hyperdimensional Representations
Apr 16, 2026Shay Snyder, Andrew Capodieci, David Gorsich +1Hyperdimensional Computing Vector Symbolic Architectures
George Mason University · George Mason University, Fairfax, Virginia, USA · Neya Robotics +3
FedUHD: Unsupervised Federated Learning using In-Memory Hyperdimensional Computing
Aug 16, 2025You Hak Lee, Keming Fan, Xiaofan Yu +4Compute-in-Memory Federated Learning Aggregation
University of California San Diego, USA
BiHDTrans: binary hyperdimensional transformer for efficient multivariate time series classification
Date pendingJingtao Zhang, Yi Liu, Qi Shen +1Efficient Neural Network Inference Transformer
School of Biomedical Engineering, Shenzhen Campus of Sun Yat-sen University · College of Medicine and Biological Information Engineering, Northeastern University

Oct 7, 2026, cs.LGJ/K move · Enter open · S save

Phase-HDC: Replacing Optimizer History with Gradient Thresholds in Discrete Phase Learning

Ahmed Nebli

Mathalyse Research

Memory-Efficient Training Sign-Based Optimization Hyperdimensional Computing

Open paper AskPDF arXiv

Training a compact model often needs far more memory than storing it, because the optimizer keeps its own records of past gradients. For a hyperdimensional classifier whose learned parameters are low-bit angles, which we call a \emph{phase memory}, these records take several times more memory than the model itself. We ask whether such a model can be trained while storing nothing but the model. The proposed method, Phase-HDC, turns each stored angle by at most one step per update, against the sign of its current gradient, and only when that gradient is large enough. We show that this simple rule is the exact solution of a first-order loss model in which every changed parameter pays a fixed cost. When everything except the update rule is held fixed, Phase-HDC matches the accuracy of Adam with 6-bit moments while storing three times less. Across eleven image, tabular, and text datasets, it stores 16--23

\times

less than standard float32 Adam and 4--6

\times

less than 8-bit Adam. The price is an average loss of about five accuracy points against float32 Adam, while Phase-HDC is more accurate than 8-bit Adam on six of the eleven datasets, including byte-level text prediction, where 8-bit Adam collapses. Instrumented training runs explain these outcomes. Once parameters must sit on a discrete grid, Adam's moments mainly decide whether a parameter moves at all, a decision that a threshold on the current gradient can make without memory, and coarse quantization of the moments breaks this decision for inputs that the data rarely contain. The storage savings are logical state rather than measured hardware memory.

Momentum

Related topics

Latest papers 24