DAOC provides stable clustering for large networks.
problem Stable clustering of large networks with accuracy and robustness.
method DAOC uses Overlap Decomposition for deterministic fine-grained clusters and Mutual Maximal Gain for robustness.
result DAOC yields stable clusters that are 25% more accurate than state-of-the-art deterministic algorithms.
Stable density-based clustering via multiparameter persistence.
problem Density-based clustering stability to data perturbations.
method Degree-Rips construction, correspondence-interleaving distance, multiparameter stability analysis.
result Persistable pipeline yields stable, consistent density-based clustering.
Proposes a new model for clustering with heavier tails.
problem Clustering with heavy-tailed data.
method Finite mixture of skewed sub-Gaussian stable distributions, maximum likelihood estimation, EM algorithm.
result The proposed model can robustly handle heavy-tailed data.
New invariant measures loop iterations in algebraic structures.
problem Measuring the asymptotic behavior of loop iterations in algebraic structures.
method Introduced sign stability and cluster stretch factor to measure loops.
result Cluster algebraic entropies match cluster stretch factor.
New criterion selects optimal number of clusters based on stability.
problem Challenges in selecting optimal number of clusters in non-parametric clustering.
method Proposes a stability-based validation criterion combining between-cluster and within-cluster stability.
result Empirically demonstrates effectiveness in selecting optimal number of clusters.
This paper optimizes cryptocurrency portfolios by clustering price correlations and improving risk-return profiles.
problem Volatility and regulatory uncertainty in cryptocurrency markets make portfolio construction challenging.
method The paper combines network analysis, price forecasting, and portfolio theory to identify stable groups of correlated cryptocurrencies.
result Predictive consensus-clustering portfolios maintain positive and stable performance up to a 14-day horizon, with favourable gain-loss asymmetry and tighter tail-risk control.
Convex clustering solves a stable optimization problem for clustering.
problem Clustering with stable and scalable solutions.
method Solving a convex optimization problem with a single tuning parameter.
result The optimization problem has a unique global minimizer stable to inputs.
We apply our statistically deterministic machine learning/clustering algorithm *K-means (recently developed in https://ssrn.com/abstract=2908286) to 10,656 published exome samples for 32 cancer types. A majority of cancer types exhibit mutation clustering structure. Our results are in-sample stable. They are also out-o…
A novel framework interprets driving patterns using Action phases clustering.
problem Challenges in comprehending driving heterogeneity from underlying behavior mechanisms.
method Resampling and Downsampling Method (RDM) followed by iterative clustering calibration.
result Six driving patterns identified in real-world datasets, revealing dynamic nature of driving.
Ball k-means reduces point-centroid distance computations for faster k-means clustering.
problem Efficiently finding k-means clusters in large datasets.
method Uses a ball to describe clusters, dividing them into stable and active areas, and adjusting points within annulus areas.
result Significantly reduces point-centroid distance computations, making k-means faster and more efficient.
The paper provides guarantees for clustering validity without distributional assumptions.
problem Validating clustering results without distributional assumptions.
method Generic method to obtain post-inference guarantees of near-optimality and stability for clustering.
result The guarantees do not depend on distributional assumptions but depend on the data set admitting a stable clustering.
Proves least Gaussian perimeter decomposition conjectures for 2-3 cells in n-dimensional space.
problem Finding least perimeter ways to divide space into cells of prescribed Gaussian measure.
method Analyzes stable clusters and uses Voronoi cells of equidistant points.
result Simplicial clusters are unique minimizers for 2-3 cells in n-dimensional space.
Quickshift++ improves clustering stability and performance.
problem Improving initial seedings for clustering algorithms.
method Provably good initial seedings for Quick Shift clustering.
result Statistical consistency and strong clustering performance.
S3VDC improves DC methods for scalability, stability, and simplicity.
problem Poor scalability, instability, and lack of simplicity in DC methods.
method Four algorithmic improvements: initial γ-training, periodic β-annealing, mini-batch GMM initialization, and inverse min-max transform. S3VDC incorporates all improvements. result S3VDC outperforms state-of-the-art methods on benchmark and industrial datasets.
The paper develops a Galois theory for cluster algebras and Riemann surfaces.
problem Building a correspondence between cluster subalgebras and automorphism groups.
method Introducing Galois-like extensions and automorphism groups for cluster algebras.
result Conditions for Galois-like extensions and properties of cluster automorphism groups.
Cluster stability selection improves feature selection in correlated data.
problem Feature selection stability in correlated data.
method Cluster stability selection exploiting known cluster structure.
result Better predictive performance than lasso alone and stability selection.
Recurrent neural networks trained on regular languages exhibit stable states that can recover from noise.
problem Stability of internal states in recurrent neural networks trained on regular languages.
method Empirical study with analysis of network activation and transitions between states.
result Recurrent neural networks trained on regular languages can recover from random perturbations and maintain stable states.
A popular method for selecting the number of clusters is based on stability arguments: one chooses the number of clusters such that the corresponding clustering results are "most stable". In recent years, a series of papers has analyzed the behavior of this method from a theoretical point of view. However, the results …
We extend Heston model with jumps to analyze volatility and implied volatility.
problem Analyzing implied volatility and volatility clustering in financial markets.
method Introducing an affine extension of the Heston model with α-stable jumps. result Examined jump clustering phenomenon and provided a jump cluster decomposition.
HiPart offers an efficient, interactive tool for hierarchical clustering.
problem Efficient and interpretable hierarchical clustering for Big Data.
method Divisive hierarchical clustering algorithms with interactive visualizations.
result High computational efficiency and interpretability in Big Data applications.
A new t-k-means algorithm improves clustering stability and robustness.
problem Poor performance and instability of standard k-means on heavy-tailed data. method Proposes t-k-means, a robust and stable variant of k-means. result Demonstrates improved stability and robustness on datasets with outliers.
A novel multi-clustering method based on boosting improves hierarchical clustering quality.
problem Improving hierarchical clustering quality in flat clustering problems.
method A boosting iteration with weighted random sampling of elements from the original dataset, followed by hierarchical clustering on each subsample and consensus combination.
result The proposed method provides superior quality solutions compared to standard hierarchical clustering methods.
Improved spectral clustering for community detection in networks.
problem Community detection in networks.
method Improved spectral clustering (ISC) based on k-means clustering on weighted eigenvectors of a regularized Laplacian matrix.
result ISC yields stable consistent community detection under mild conditions and outperforms classical methods.
Dual regularized graph Laplacian improves spectral clustering for community detection.
problem Detecting clusters in networks with improved spectral clustering methods.
method Proposes dual regularized graph Laplacian for three spectral clustering approaches.
result Theoretical analysis shows DRSC and DRSLIM yield stable consistent community detection.
Unified framework for differentiable graph partitioning with probabilistic cuts.
problem Lack of general guarantees and principled gradients in prior probabilistic relaxations of graph cuts.
method Unified probabilistic framework covering a wide class of cuts, including Normalized Cut, with tight analytic upper bounds.
result Rigorous, numerically stable foundation for scalable, differentiable graph partitioning.
Text clustering method replaces centroids with summaries for interpretability and scalability.
problem Efficiently clustering text data while maintaining interpretability and scalability.
method k-NLPmeans and k-LLMmeans, which periodically replace numeric centroids with textual summaries.
result Consistently outperforms classical baselines and recent LLM-based clustering methods.
Extends convex clustering to graph-structured data.
problem Handling graph-structured data with convex clustering.
method Formulates a convex objective and uses a proximal dual algorithm for efficient recovery.
result Demonstrates the effectiveness of the method on real-life datasets.
Collimated streams of particles produced in high energy physics experiments are organized using clustering algorithms to form jets. To construct jets, the experimental collaborations based at the Large Hadron Collider (LHC) primarily use agglomerative hierarchical clustering schemes known as sequential recombination. W…
MMGAN stabilizes GANs for multi-modal data clustering.
problem Stability and data distribution loss in GANs for multi-modal data.
method Model latent space as Gaussian mixture model, clusters data manifolds, and trains with clustering network.
result MMGAN outperforms state-of-the-art models in clustering multi-modal data.
Algorithm identifies and transfers unstable features to create robust classifiers.
problem Developing unbiased classifiers from input-label pairs alone.
method Contrast different data environments in source tasks to encode unstable features, then cluster target task data and minimize worst-case risk.
result Our method maintains robustness across synthetic and real-world environments.
Data aggregation improves HAC for resource-constrained systems.
problem Resource constraints in embedded systems limit HAC's applicability.
method Data aggregation with BETULA algorithm reduces memory and runtime requirements.
result HAC can be applied to large datasets on resource-constrained systems.
Introduces robust convex clustering with Median of Means for better data clustering.
problem Challenges in convex clustering with high-dimensional data and noise/outliers.
method Integrates convex clustering with Median of Means estimator for robustness and efficiency.
result Enhanced clustering performance on large-scale datasets compared to existing methods.
We develop a model to cluster time-series data with interval censoring, improving disease phenotyping.
problem Noise and interval censoring hinder clustering in disease phenotyping.
method Deep generative, continuous-time model that clusters time-series data while correcting for censorship.
result Our model corrects for interval censoring and recovers known clinical subtypes.
A new graph-based clustering method for moderate-dimensional data.
problem Performance degradation of existing graph-based clustering methods in high dimensions.
method Introduces UN-CCDs using NND-based MC-SRT for covering radii determination.
result UN-CCDs provide stable and competitive performance in moderate-sized datasets.
MFCVAE clusters data over multiple facets, improving disentanglement and generation.
problem Clustering high-dimensional data like images over multiple characteristics.
method Variational autoencoder with hierarchical latent variables and Mixture-of-Gaussians priors.
result MFCVAE learns and clusters over multiple aspects of data in a disentangled manner.
DynMSA detects market clusters for better portfolio allocation.
problem Identifying stable market clusters for effective portfolio management.
method Combining Random Matrix Theory with modularity optimization and spectral clustering.
result DynMSA outperforms baseline models in intra- and inter-cluster correlation differences.
Proposes a novel approach for cluster-aware matching using Laplacian Optimal Transport.
problem Matching point clouds with intrinsic cluster structure requires robust region-to-region alignment over precise point-to-point correspondence.
method Laplacian Optimal Transport (LapOT) with regularization for cluster-aware matching and Refined Simultaneous Clustering (RSC) for consistent partitions.
result Laplacian Optimal Transport produces more consistent and meaningful alignments between point clouds.
GCAO improves clustering of high-dimensional data by grouping low-density boundary points.
problem Stability and accuracy of clustering in high-dimensional, non-uniform data.
method Group-level optimization with gravitational attraction and optimization.
result GCAO outperforms 11 clustering methods on multiple datasets.
Improved BIRCH clustering method to avoid numeric issues.
problem Numeric instability in BIRCH clustering.
method Introduced a new cluster feature to replace the sum of squares, avoiding catastrophic cancellation.
result The new method is more numerically stable and efficient.
Study evaluates clustering methods for Google Trends data.
problem Clustering high-dimensional, noisy time series data.
method Symbolic Aggregate Approximation (SAX), Enhanced SAX (eSAX), and Topological Data Analysis (TDA).
result TDA provides more balanced and meaningful groupings than SAX and eSAX.
HD-BWDM improves clustering validation in high-dimensional data.
problem Determining the right number of clusters in high-dimensional data.
method HD-BWDM integrates random projection, PCA, trimmed clustering, and medoid-based distances.
result HD-BWDM remains stable and interpretable under high-dimensional projections and contamination.
We propose a combination of cluster analysis and stochastic process analysis to characterize high-dimensional complex dynamical systems by few dominating variables. As an example, stock market data are analyzed for which the dynamical stability as well as transitions between different stable states are found. This comb…
This paper proposes a decentralized reinforcement learning method for multi-agent resource allocation.
problem Allocating heterogeneous resources among multiple agents in a decentralized manner.
method Liquid-Graph-Time Clustering-IPPO, integrating dynamic cluster consensus.
result LGTC-IPPO achieves more stable rewards, better coordination, and robust performance.
A method for learning embeddings from multi-view data using Gromov-Wasserstein.
problem Challenges in learning low-dimensional representations from multi-view relational data with differing geometries.
method Bary-GWMDS and Mean-GWMDS-C, Gromov-Wasserstein-based methods operating on distance matrices.
result Stable and geometrically meaningful embeddings learned from synthetic and real-world datasets.
DIVI clusters noisy high-dimensional data with stable feature gating.
problem Challenging clustering in high-dimensional noisy data.
method Data-informed variational clustering framework combining global feature gating and adaptive structure growth.
result DIVI performs competitively under severe feature noise and remains computationally feasible.
Paper uses NLP to cluster patient visits for diagnosis validation.
problem Validating if similar patients receive similar diagnoses.
method Representation of medical visits using word embeddings, clustering patients' visits.
result Stable and separated segments of visits positively validated against diagnoses.
DSPM models control noise volatility, improving financial data analysis.
problem Financial returns exhibit volatility clustering, challenging traditional models.
method DSPM uses a tempered-stable subordinator to control noise volatility, preserving kurtosis and autocorrelation.
result DSPM models accurately capture volatility clustering and noise mechanisms.
Robust fuzzy clustering for EEG driver alertness with outlier detection.
problem Ambiguous state boundaries in multivariate time series data.
method RFCPCA, a robust fuzzy subspace-clustering method for MTS.
result RFCPCA improves clustering accuracy and characterizes uncertainty and outliers in MTS.