Least squares quantization in PCM

By S. Lloyd. 1982

Subfields: Optimization & Training, Speech & Audio

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Optimization & Training

In Speech & Audio

Citations in the corpus

Local Aggregation for Unsupervised Learning of Visual Embeddings (2019, methodology): “In computing Ci, we use kmeans [48] implemented in Faiss [38] as the standard unsupervised clustering algorithm, generating multiple clusterings for robustness via different random initializations.”
HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units (2021, methodology): “k-means algorithm [55] for acoustic unit discovery by default.”
Unsupervised Learning by Predicting Noise (2017, methodology): “Our approach also shares some similarities with standard clustering approches like k -means (Lloyd, 1982) or discriminative clustering (Bach & Harchaoui, 2007).”
Meta-Learning for Semi-Supervised Few-Shot Classification (2018, methodology): “In addition to the original k -Means method (Lloyd, 1982), the most related work to our setup involving clustering algorithms considers applying k -Means in the presence of outliers (Hautamäki et al., 2005; Chawla & Gionis, 2013; Gupta et al., 2017).”
SoundStream: An End-to-End Neural Audio Codec (2021, methodology): “Optimal scalar quantization based on Lloyd’s algorithm [25] can be extended to a high-dimensional space via the generalized Lloyd algorithm (GLA) [26], which is very similar to k-means clustering [27].”
Breaking the Communication-Privacy-Accuracy Trilemma (2020, methodology): “Lloyd’s algorithm [19] for k-means clustering or the power-iteration method for PCA can also be reduced to the mean estimation task.”
Federated Learning and Differential Privacy: Software tools analysis, the Sherpa.ai FL framework and methodological guidelines for preserving data privacy (2020, background): “One example is found in the k-means clustering algorithm for unsupervised learning [35, 36], where the non-IID nature of the data distribution is seen as a major obstacle in a federated setting.”
cpSGD: Communication-efficient and differentially-private distributed SGD (2018, background): “DME is a fundamental building block for many distributed learning algorithms including distributed PCA/clustering [24].”
Distributed Mean Estimation with Limited Communication (2016, methodology): “For example, in Lloyd’s algorithm [18] for k-means clustering, if data is distributed across several clients, the server needs to compute the means of all clusters in each update step.”
Bayesian Nonparametric Federated Learning of Neural Networks (2019, background): “clustering (Lloyd, 1982) of vectors constructed by concatenating weights and biases of local neural networks.”
RepCodec: A Speech Representation Codec for Speech Tokenization (2023, methodology): “Both k-means (Lloyd, 1982) and VQ (Gray, 1984) are algorithms to discretize a high-dimensional vector into a discrete label.”
Multimodal Distributional Semantics (2013, methodology): “We use an approximated version of k-means called Lloyd’s algorithm (1982) as implemented in the VLFeat toolbox.”
Making AI Forget You: Data Deletion in Machine Learning (2019, methodology): “As a baseline, we use the canonical Lloyd’s algorithm initialized by k -means++ seeding [53, 5].”
Community detection in graphs (2009, methodology): “The procedure, as described, proceeds deterministically from the given initial partition, as one shifts systematically the vertex with lowest fitness, and is likely to get trapped in local optima.”
Computing and Rendering Point Set Surfaces (2003, methodology): “This idea is related to Lloyd’s method [37], i.e., techniques using Voronoi diagrams to achieve a certain distribution of points [40].”
A survey of kernel and spectral methods for clustering (2008, methodology): “A simple algorithm able to construct a Voronoi tessellation of the input space was proposed in 1957 by Lloyd [46] and it is known as batch K-means.”