Adaptive Functional Clustering with Structured Dependence via Variational Inference
Abstract
Functional clustering is an important tool for identifying latent heterogeneity in functional data and has been widely applied across various scientific fields. However, many existing methods are not fully adaptive, as they may require the number of clusters to be prespecified and may lack automatic control over the smoothness of the underlying functions. They also commonly assume independent and identically distributed errors, thereby overlooking additional within-curve dependence. We propose a fully adaptive Bayesian procedure for functional clustering that addresses these limitations through Dirichlet process priors, adaptive smoothness control, and flexible covariance modeling. For computational scalability, the proposed method employs variational inference as an efficient alternative to Markov chain Monte Carlo. Together, these features provide a unified Bayesian framework for functional clustering and cluster-specific mean function estimation in the presence of structured within-curve dependence.
Related
- Variational Inference for Functional Data Clustering via Dirichlet Process Mixtures with Correlated Errors
- Asymptotically Valid Laplace Variational Inference for Bayesian Nonparametric Clustering of Marked Point Patterns
- Amortized Structured Stochastic Variational Inference for Gaussian Process Latent Variable Models
- Clustering extremal dependence structures via Wasserstein distances between angular measures
- Convergence of Coordinate Ascent Variational Inference for log-concave measures via optimal transport
BibTeX
@misc{lee2026adaptive,
title = {{Adaptive Functional Clustering with Structured Dependence via Variational Inference}},
author = {Seojin Lee and Neulpum Jeong and Seonghyun Jeong},
howpublished = {arXiv},
year = {2026},
month = aug,
doi = {10.48550/arxiv.2608.29619},
eprint = {2608.29619},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.29619},
}
RIS
TY - UNPB
TI - Adaptive Functional Clustering with Structured Dependence via Variational Inference
AU - Seojin Lee
AU - Neulpum Jeong
AU - Seonghyun Jeong
PY - 2026
DA - 2026/08/30
PB - arXiv
DO - 10.48550/arxiv.2608.29619
UR - https://arxiv.org/abs/2608.29619
AB - Functional clustering is an important tool for identifying latent heterogeneity in functional data and has been widely applied across various scientific fields. However, many existing methods are not fully adaptive, as they may require the number of clusters to be prespecified and may lack automatic control over the smoothness of the underlying functions. They also commonly assume independent and identically distributed errors, thereby overlooking additional within-curve dependence. We propose a fully adaptive Bayesian procedure for functional clustering that addresses these limitations through Dirichlet process priors, adaptive smoothness control, and flexible covariance modeling. For computational scalability, the proposed method employs variational inference as an efficient alternative to Markov chain Monte Carlo. Together, these features provide a unified Bayesian framework for functional clustering and cluster-specific mean function estimation in the presence of structured within-curve dependence.
ER -