Advances in Data Analysis and Classification最新文献

Special issue on “Data modelling for dimension reduction, clustering and classification with complex data” “复杂数据降维、聚类和分类的数据建模”特刊

IF 2.1 4区计算机科学

Advances in Data Analysis and Classification Pub Date : 2026-08-19 DOI: 10.1007/s11634-026-00708-2

Mark de Rooij, Michele La Rocca, Andrea Cerioli

引用次数: 0

Depth-winsorized PICARD: a discussion on “Independent component analysis by robust distance correlation” 深度winsorized PICARD：关于“鲁棒距离相关独立分量分析”的讨论

IF 2.1 4区计算机科学

Advances in Data Analysis and Classification Pub Date : 2026-08-19 DOI: 10.1007/s11634-026-00707-3

Giovanni C. Porzio, Simona Balzano, Houyem Demni

引用次数: 0

Rejoinder to comments on “Independent component analysis by robust distance correlation” 对“鲁棒距离相关的独立分量分析”评论的回答

IF 2.1 4区计算机科学

Advances in Data Analysis and Classification Pub Date : 2026-08-17 DOI: 10.1007/s11634-026-00706-4

Sarah Leyder, Jakob Raymaekers, Peter J. Rousseeuw, Tom Van Deuren, Tim Verdonck

引用次数: 0

Discussion of “Independent component analysis by robust distance correlation”: toward a functional view of robust ICA “鲁棒距离相关的独立分量分析”的讨论：从鲁棒独立分量分析的功能观点出发

IF 2.1 4区计算机科学

Advances in Data Analysis and Classification Pub Date : 2026-08-14 DOI: 10.1007/s11634-026-00693-6

Alexander Schell

引用次数: 0

Modeling and estimating skewed and heavy-tailed populations via unsupervised mixture models 通过无监督混合模型建模和估计偏态和重尾种群

IF 2.1 4区计算机科学

Advances in Data Analysis and Classification Pub Date : 2026-07-07 DOI: 10.1007/s11634-026-00703-7

Marco Bee, Flavio Santi

引用次数: 0

Sub-topics detection with extended flexible latent Dirichlet allocation 扩展柔性潜狄利克雷分配子主题检测

IF 2.1 4区计算机科学

Advances in Data Analysis and Classification Pub Date : 2026-07-01 DOI: 10.1007/s11634-026-00690-9

Roberto Ascari, Alice Giampino, Sonia Migliorati

{"title":"Sub-topics detection with extended flexible latent Dirichlet allocation","authors":"Roberto Ascari, Alice Giampino, Sonia Migliorati","doi":"10.1007/s11634-026-00690-9","DOIUrl":"10.1007/s11634-026-00690-9","url":null,"abstract":"<div><p>The rapid expansion of digital data has intensified the need for computational methods capable of analyzing complex latent structures across a variety of domains, including textual data. Latent topic models, particularly latent Dirichlet allocation (LDA), are widely used to uncover latent structures in large text corpora. However, the Dirichlet prior on topic proportions imposes structural limitations that reduce the model’s ability to capture complex dependencies among topics. In this paper, we introduce the extended flexible latent Dirichlet allocation (EFLDA), a probabilistic model that extends LDA by allowing richer patterns of dependence among topics. The enriched parametrization of EFLDA improves the model’s ability to represent complex thematic structures, leading to great interpretability in real-world settings. Furthermore, we introduce the concept of sub-topics, defined as specific combinations of topics that provide a deeper understanding of corpora. We develop a collapsed Gibbs sampler for efficient inference and conduct an extensive evaluation on both synthetic data and multiple real-world applications, including mental health discourse, news articles, and microbiome data. Empirical results show that EFLDA outperforms classical LDA and recent alternative approaches in terms of topic coherence, sub-topic detection, and interpretability, while remaining robust across heterogeneous data settings characterized by complex and overlapping latent structures.</p></div>","PeriodicalId":49270,"journal":{"name":"Advances in Data Analysis and Classification","volume":"20 3","pages":"965 - 997"},"PeriodicalIF":2.1,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s11634-026-00690-9.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148926420","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Considerations for robust ICA: a discussion of the PICARD framework 健壮ICA的考虑：PICARD框架的讨论

IF 2.1 4区计算机科学

Advances in Data Analysis and Classification Pub Date : 2026-06-29 DOI: 10.1007/s11634-026-00702-8

Francesca Greselin, Giorgia Zaccaria

引用次数: 0

Discussion on “Independent component analysis by robust distance correlation” by Leyder et al. (2026) 对Leyder等人（2026）“鲁棒距离相关独立分量分析”的讨论

IF 2.1 4区计算机科学

Advances in Data Analysis and Classification Pub Date : 2026-06-29 DOI: 10.1007/s11634-026-00700-w

Angela Montanari, Cinzia Viroli

{"title":"Discussion on “Independent component analysis by robust distance correlation” by Leyder et al. (2026)","authors":"Angela Montanari, Cinzia Viroli","doi":"10.1007/s11634-026-00700-w","DOIUrl":"10.1007/s11634-026-00700-w","url":null,"abstract":"<div><p>Leyder et al. (2026) make an important contribution to robust independent component analysis by introducing PICARD, a sequential procedure that estimates independent sources through a robust dependence criterion based on distance correlation. A central role is played by the bowl transform, which maps far outlying observations close to the origin while remaining continuous and injective, thereby preserving the characterization of independence through vanishing distance correlation. In this discussion, we focus on the statistical role of this transformation within the overall robustness of PICARD. We argue that the bowl transform is not only a device for robustifying a dependence measure, but also induces a geometry that can be interpreted in terms of observation weighting. This leads to two related weighting schemes: one based on the norm of the bowl-transformed observations, and one based on the radial component of the transform. To isolate the effect of such weights, we examine them in a simple projection pursuit setting, which provides a natural projection-based counterpart to ICA. The resulting exploratory study suggests that bowl-induced weights can transfer part of the robustness mechanism of PICARD to projection-based procedures. More broadly, the discussion highlights the importance of disentangling the contributions of robust whitening, bowl-transform geometry, and robust distance correlation in explaining the empirical success of PICARD.</p></div>","PeriodicalId":49270,"journal":{"name":"Advances in Data Analysis and Classification","volume":"20 3","pages":"783 - 787"},"PeriodicalIF":2.1,"publicationDate":"2026-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s11634-026-00700-w.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148928073","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

New distance-based robust clustering algorithms for large mixed-type data 基于距离的大型混合类型数据鲁棒聚类新算法

IF 2.1 4区计算机科学

Advances in Data Analysis and Classification Pub Date : 2026-06-26 DOI: 10.1007/s11634-026-00701-9

Aurea Grané, Fabio Scielzo-Ortiz

引用次数: 0

Discussion to the paper “Independent component analysis by robust distance correlation” 对“鲁棒距离相关的独立分量分析”一文的讨论

IF 2.1 4区计算机科学

Advances in Data Analysis and Classification Pub Date : 2026-06-25 DOI: 10.1007/s11634-026-00694-5

Klaus Nordhausen, Una Radojičić, Perttu Saarela, Sara Taskinen

引用次数: 0