paper-with-me

홈 › Papers

t-SNE Exaggerates Clusters, Provably

2025-10-09 · Noah Bergam, Szymon Snoeck, Nakul Verma arxiv

Central to the widespread use of t-distributed stochastic neighbor embedding (t-SNE) is the conviction that it produces visualizations whose structure roughly matches that of the input. To the contrary, we prove that (1) the strength of the input clustering, and (2) the extremity of outlier points, cannot be reliably inferred from the t-SNE output. We demonstrate the prevalence of these failure modes in practice as well.

📄 PDF Abstract BibTeX arXiv:2510.07746

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Bipartite Stochastic Block Models with Tiny Clusters

2018-12-01 · NeurIPS 2018 12 · Stefan Neumann

We study the problem of finding clusters in random bipartite graphs. We present a simple two-step algorithm which provably finds even tiny clusters of size $O(n^\epsilon)$, where $n$ is the number of vertices in the grap…

Provably Personalized and Robust Federated Learning

2023-06-14 · Mariel Werner, Lie He, Michael Jordan, Martin Jaggi 외

Identifying clients with similar objectives and learning a model-per-cluster is an intuitive and interpretable approach to personalization in federated learning. However, doing so with provable and optimal guarantees has…

ClusteringFederated LearningPersonalized Federated LearningStochastic Optimization

Efficient Algorithms for Generating Provably Near-Optimal Cluster Descriptors for Explainability

2020-02-06 · Prathyush Sambaturu, Aparna Gupta, Ian Davidson, S. S. Ravi 외

Improving the explainability of the results from machine learning methods has become an important research goal. Here, we study the problem of making clusters more interpretable by extending a recent approach of [Davidso…

Bipartite Correlation Clustering -- Maximizing Agreements

2016-03-09 · Megasthenis Asteris, Anastasios Kyrillidis, Dimitris Papailiopoulos, Alexandros G. Dimakis

In Bipartite Correlation Clustering (BCC) we are given a complete bipartite graph $G$ with `+' and `-' edges, and we seek a vertex clustering that maximizes the number of agreements: the number of all `+' edges within cl…

Clustering

VET: A Framework for Analyzing AI Discourse

2026-06-01 · Meredith Ringel Morris arxiv

Public discourse on AI has become polarized; exaggerated positions on AI in traditional and social media threaten the development of AI Literacy among the general public. In this article, I introduce the VET Framework, a…