azoai

Dynamic Neural Codebooks Boost Vector Quantization

In an article recently posted to the Meta Research website, researchers focused on improving vector quantization for data compression and vector search. They introduced quantization with implicit ...
IEEE

Vector Quantization With Error Uniformly Distributed Over an Arbitrary Set

Abstract: For uniform scalar quantization, the error distribution is approximately a uniform distribution over an interval (which is also a 1-dimensional ball ...
GitHub

qiziAI/forked-vector-quantize-pytorch

A vector quantization library originally transcribed from Deepmind's tensorflow implementation, made conveniently into a package. It uses exponential moving averages to update the dictionary. VQ has ...
Nature

Vector Quantization and Learning Algorithms

Vector quantisation and its associated learning algorithms form an essential framework within modern machine learning, providing interpretable and computationally efficient methods for data ...
IEEE

Vector Quantization for Deep-Learning-Based CSI Feedback in Massive MIMO Systems

Abstract: This letter presents a finite-rate deep-learning (DL)-based channel state information (CSI) feedback method for massive multiple-input multiple-output (MIMO) systems. The presented method ...
marktechpost

Qualcomm AI Research Proposes the GPTVQ Method: A Fast Machine Learning Method for Post-Training Quantization of Large Networks Using Vector Quantization (VQ)

Efficiency of Large Language Models (LLMs) is a focal point for researchers in AI. A groundbreaking study by Qualcomm AI Research introduces a method known as GPTVQ, which leverages vector ...
GitHub

Kitsunetic/vector-quantize-pytorch-cuda

A vector quantization library originally transcribed from Deepmind's tensorflow implementation, made conveniently into a package. It uses exponential moving averages to update the dictionary. VQ has ...
Design-Reuse

Pyramid Vector Quantization and Bit Level Sparsity in Weights for Efficient Neural Networks Inference

This paper discusses three basic blocks for the inference of convolutional neural networks (CNNs). Pyramid Vector Quantization [1] (PVQ) is discussed as an effective quantizer for CNNs weights ...