Randomized Hadamard Transforms

Follow this topic Ask about this topic

Momentum

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

Jul 6Week of Sep 21

Latest papers 16

All topics

RSLM: Training-Free Vector Quantization for Approximate Nearest Neighbor Search
Aug 31, 2026Rastislav Lenhardt, Teodora Dobos, Thomas Vecchiato +2Residual Vector Quantization Approximate Nearest-Neighbor Search
Google Zurich, Switzerland · Technical University of Munich Munich, Germany · University of Copenhagen Copenhagen, Denmark +1
Qubit-Efficient Quantum Search for Hyperdimensional Decomposition via Logarithmic Encoding
Jul 11, 2026Sanggeon Yun, Hyunwoo Oh, Ryozo Masukawa +2Quantum Error Correction Quantum Circuits
University of California, Irvine
HyperQuant: A Rate-Distortion-Optimal Quantization Pipeline for Large Language and Diffusion Models
Jun 22, 2026Yuval Domb, Hadar Sackstein, Tomer SolbergPost-Training Quantization Qantis
ShearFuse-UNet: Hadamard, DCT, and Shearlet Transform Fusion for Next-Day Wildfire Spread Prediction
Jun 12, 2026Ene Meco, Yingyi Luo, Emadeldeen Hamdan +2Wildfire Prediction U-Net
Department of Electrical and Computer Engineering, University of Illinois Chicago, Chicago, IL 60607 USA · US Forest Service, Pacific Wildland Fire Science Laboratory, Seattle, WA 98103 USA
Adversarial Attack and Disturbance Detection by Hadamard-Coded Output Representations for Object Detection and Semantic Segmentation
Jun 8, 2026Lucas Görnhardt, Timo Bartels, Niklas Schwarz +1Semantic Segmentation Object Detection
Technische Universität Braunschweig, Germany
Riemannian Optimization for Hadamard Products of Low-Rank Matrices
May 31, 2026Pratik Jawanpuria, Ankish Chandresh, Bamdev MishraRiemannian Optimization Low-Rank Structure
Centre for Machine Intelligence and Data Science, Indian Institute of Technology Bombay, India · Microsoft India
HARP: Hadamard-Preconditioned Adaptive Rotation Processor for Extreme LLM Quantization
May 28, 2026Artur Zagitov, Gleb Molodtsov, Aleksandr BeznosikovPost-Training Quantization Large Language Model Quantization
1MIRAI · 2BRAIn Lab · 3Innopolis University
How Much Is a Dataset Worth? Scaling Laws, the Vendi Score, and Matrix Spectral Functions
May 28, 2026Jeff A. Bilmes, Gantavya Bhatt, Arnav M. DasBenchmark Datasets Destination-Only Scoring
Department of Electrical & Computer Engineering 2Paul G. Allen School of Computer Science & Engineering University of Washington, Seattle Seattle, WA 98195
Manifold-based Algorithms for the Hadamard Decomposition
May 27, 2026Nicolas Gillis, Subhayan Saha, Stefano Sicilia +1Randomized Hadamard Transforms Singular Value Decomposition
Department of Mathematics and Operational Research, University of Mons, Mons, Belgium. · SS is a member of the Gruppo Nazionale Calcolo Scientifico-Istituto Nazionale di Alta Matematica (GNCS-INdAM).
QAM-W: Joint 2D Codebook Quantization for LLM Weights via Hadamard Rotation and Activation-Aware Scaling
May 25, 2026Preetam Sharma, Kacper DobekModel Weights Randomized Hadamard Transforms
Independent Research · Institute of Computing Science Poznan University of Technology, Poznan, Poland
Provable Quantization with Randomized Hadamard Transform
May 13, 2026Ying Feng, Piotr Indyk, Michael Kapralov +2Randomized Hadamard Transforms Residual Vector Quantization
Quantizing With Randomized Hadamard Transforms: Efficient Heuristic Now Proven
May 7, 2026Ran Ben-Basat, William Kuszmaul, Michael Mitzenmacher +2Randomized Hadamard Transforms Residual Vector Quantization
UCL and Broadcom · Carnegie Mellon University · Harvard University +2
The Banach-Butterfly Invariant: Influence-Adaptive Walsh Geometry for Ternary Polynomial Threshold Functions
May 2, 2026Gorgi PavlovPolynomials Decision Thresholds
Lehigh University · Johnson and Johnson
Approximating Uniform Random Rotations by Two-Block Structured Hadamard Rotations in High Dimensions
Apr 25, 2026Tomer Zilca, Gal MendelsonRandomized Hadamard Transforms Random
Faculty of Data and Decision Sciences, Technion – Israel Institute of Technology, Haifa, Israel · Edward P. Fitts Department of Industrial and Systems Engineering, North Carolina State University, Raleigh, NC, USA
SAW-INT4: System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving
Apr 21, 2026Jinda Jia, Jisen Li, Zhongzhu Zhou +8Key-Value Cache Quantization Key-Value Cache Compression
Together AI
Toward Generalizable Deep Learning Based Peatland Fire Detection via Walsh Hadamard Transform and Domain Adaptation
Mar 2, 2026Emadeldeen Hamdan, Ahmad Faiz Tharima, Mohd Zahirasri Mohd Tohir +4Wildfire Detection Resnet-18
Department of Electrical and Computer Engineering, University of Illinois Chicago, Chicago, IL, USA · Fire and Rescue Department of Malaysia, Malaysia · Dept. of Chemical and Environmental Engineering, Faculty of Engineering, Universiti Putra Malaysia, Malaysia. +2

Aug 31, 2026, cs.LGJ/K move · Enter open · S save

RSLM: Training-Free Vector Quantization for Approximate Nearest Neighbor Search

Rastislav Lenhardt, Teodora Dobos, Thomas Vecchiato, Jiri Isa+1

Google Zurich, Switzerland · Technical University of Munich Munich, Germany · University of Copenhagen Copenhagen, Denmark+1

Residual Vector Quantization Approximate Nearest-Neighbor Search Vector Database Randomized Hadamard Transforms Behavioral Embeddings Affectcodec+1

Open paper AskPDF arXiv

By introducing RSLM (Rotated Scaled Lloyd-Max), a family of training-free vector quantization codecs compressing embeddings to 1--4 bits per dimension, we reduce memory cost and memory bandwidth of a typical large-scale Approximate Nearest Neighbor (ANN) search system, while reducing its complexity and keeping or improving recall across multiple benchmark datasets. State-of-the-art systems filter candidates using coarse partitions, approximately score them to narrow the set, and then rescore the best with higher precision representations (often >=8 bits per dimension). Our relativized codecs can bring this down to 2--4 bits per dimension. We use the properties of the ANN system to encode residual vectors instead of full vectors, both for the approximate scoring phase and the rescoring phase. Since Maximum Inner Product Search (MIPS) is very sensitive to vector norms, we correct the

L_2

norms of quantized vectors. Our major innovation is that we correct the

L_2

norm of the final reconstructed vector rather than just the residual. Our rescaling replaces more complicated schemes, such as Anisotropic loss. The residualization scheme gives us a more favorable quality vs size trade-off than generic quantization methods. Our high-performance implementation leverages a block-wise cascaded Fast Walsh-Hadamard Transform (FWHT) with linear-like complexity, AVX SIMD-optimized codebooks, and a steganographic encoding of scaling factors for perfect cache-line alignment.

Momentum

Related topics

Latest papers 16