mlsanityData to 7 Oct 2026

Theoretical Foundations of t-SNE for Visualizing High-Dimensional Clustered Data

arXiv 2105.07536 ↗First posted 16 May 2021stat.ML cs.LG math.STcited by 55

Not on the map. Why?

Abstract (arXiv)

This paper investigates the theoretical foundations of the t-distributed stochastic neighbor embedding (t-SNE) algorithm, a popular nonlinear dimension reduction and data visualization method. A novel theoretical framework for the analysis of t-SNE based on the gradient descent approach is presented. For the early exaggeration stage of t-SNE, we show its asymptotic equivalence to power iterations based on the underlying graph Laplacian, characterize its limiting behavior, and uncover its deep connection to Laplacian spectral clustering, and fundamental principles including early stopping as implicit regularization. The results explain the intrinsic mechanism and the empirical benefits of such a computational strategy. For the embedding stage of t-SNE, we characterize the kinematics of the low-dimensional map throughout the iterations, and identify an amplification phase, featuring the intercluster repulsion and the expansive behavior of the low-dimensional map, and a stabilization phase. The general theory explains the fast convergence rate and the exceptional empirical performance of t-SNE for visualizing clustered data, brings forth interpretations of the t-SNE visualizations, and provides theoretical guidance for applying t-SNE and selecting its tuning parameters in various applications.

Key facts. Cited by 55 papers in the map (data through 7 Oct 2026). Builds on 13 of its 46 references that are in the map. First posted on arXiv 16 May 2021.

Builds on

13 of 46 references.

References · 13

  1. 2020Understanding How Dimension Reduction Tools Work: An Empirical Approach to Deciphering t-SNE, UMAP, TriMAP, and PaCMAP for Data Visualizationcited by 170
  2. 2017Efficient Algorithms for t-distributed Stochastic Neighborhood Embeddingcited by 75
  3. 2017Clustering with t-SNE, provablycited by 51
  4. 2018An Analysis of the t-SNE Algorithm for Data Visualizationcited by 49
  5. 2016Rate-Optimal Perturbation Bounds for Singular Subspaces with Applications to High-Dimensional Statisticscited by 45
  6. 2020t-viSNE: Interactive Assessment and Interpretation of t-SNE Projectionscited by 43
  7. 2015Approximated and User Steerable tSNE for Progressive Visual Analyticscited by 19
  8. 2021t-SNE, Forceful Colorings and Mean Field Limitscited by 10
  9. 2018Stochastic Neighbor Embedding under f-divergencescited by 9
  10. 2017Stochastic Neighbor Embedding separates well-separated clusterscited by 7
  11. 2020Tree-SNE: Hierarchical Clustering and Visualization Using t-SNEcited by 3
  12. 2020Spectral Clustering Revisited: Information Hidden in the Fiedler Vectorcited by 3
1 more
  1. 2018Dimensionality Reduction has Quantifiable Imperfections: Two Geometric Boundscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 5; 2024: 14; 2025: 11; 2026: 20.

55 papers.

Sort:

By area:

  1. 2022Your Contrastive Learning Is Secretly Doing Stochastic Neighbor Embeddingcited by 28
  2. 2026Think-Then-Generate: Reasoning-Aware Text-to-Image Diffusion with LLM Encoderscited by 15
  3. 2023SNEkhorn: Dimension Reduction with Symmetric Entropic Affinitiescited by 12
  4. 2022Learning Low-Dimensional Nonlinear Structures from High-Dimensional Noisy Data: An Integral Operator Approachcited by 8
  5. 2024Symmetric Graph Contrastive Learning against Noisy Views for Recommendationcited by 7
  6. 2022A Spectral Method for Assessing and Combining Multiple Data Visualizationscited by 6
  7. 2025The Shape of Attraction in UMAP: Exploring the Embedding Forces in Dimensionality Reductioncited by 5
  8. 2026Not Just What's There: Enabling CLIP to Comprehend Negated Visual Descriptions Without Fine-tuningcited by 5
  9. 2024Convergence analysis of t-SNE as a gradient flow for point cloud on a manifoldcited by 4
  10. 2024Large data limits and scaling laws for tSNEcited by 4
  11. 2024Assessing and improving reliability of neighbor embedding methods: a map-continuity perspectivecited by 4
  12. 2022Laplacian-based Cluster-Contractive t-SNE for High Dimensional Data Visualizationcited by 3
38 more
  1. 2023GaitSADA: Self-Aligned Domain Adaptation for mmWave Gait Recognitioncited by 3
  2. 2024Strada-LLM: Graph LLM for traffic predictioncited by 3
  3. 2025t-SNE Exaggerates Clusters, Provablycited by 3
  4. 2023CWD30: A Comprehensive and Holistic Dataset for Crop Weed Recognition in Precision Agriculturecited by 2
  5. 2024Sailing in high-dimensional spaces: Low-dimensional embeddings through angle preservationcited by 2
  6. 2025Learning Joint ID-Textual Representation for ID-Preserving Image Synthesiscited by 2
  7. 2026What Makes Position Zero Special? A Mechanistic Study of Position Zero Attention Sinks in LLMscited by 2
  8. 2023Subject clustering by IF-PCA and several recent methodscited by 1
  9. 2024Towards Transparency: Exploring LLM Trainings Datasets through Visual Topic Modeling and Semantic Framecited by 1
  10. 2024Areas of Improvement for Autonomous Vehicles: A Machine Learning Analysis of Disengagement Reportscited by 1
  11. 2024Enhanced document retrieval with topic embeddingscited by 1
  12. 2024Stochastic neighborhood embedding and the gradient flow of relative entropycited by 1
  13. 2025ScholarBench: A Bilingual Benchmark for Abstraction, Comprehension, and Reasoning Evaluation in Academic Contextscited by 1
  14. 2025Unsupervised Learning for Industrial Defect Detection: A Case Study on Shearographic Datacited by 1
  15. 2026BERT-JEPA: Reorganizing CLS Embeddings for Language-Invariant Semanticscited by 1
  16. 2026On the continuum limit of t-SNE for data visualizationcited by 1
  17. 2026Some Theoretical Limitations of t-SNEcited by 1
  18. 2026SemLT3D: Semantic-Guided Expert Distillation for Camera-only Long-Tailed 3D Object Detectioncited by 1
  19. 2022May the force be with youcited by 0
  20. 2023Efficient and Robust Bayesian Selection of Hyperparameters in Dimension Reduction for Visualizationcited by 0
  21. 2024Semi-supervised segmentation of land cover images using nonlinear canonical correlation analysis with multiple features and t-SNEcited by 0
  22. 2024Uncertainty-aware t-distributed Stochastic Neighbor Embedding for Single-cell RNA-seq Datacited by 0
  23. 2024Convergence Guarantees for the DeepWalk Embedding on Block Modelscited by 0
  24. 2024Unified dimensionality reduction techniques in chronic liver disease detectioncited by 0
  25. 2025Fast and Accurate Identification of Hardware Trojan Locations in Gate-Level Netlist using Nearest Neighbour Approach integrated with Machine Learning Techniquecited by 0
  26. 2025Drivetrain simulation using variational autoencoderscited by 0
  27. 2025Cluster and then Embed: A Modular Approach for Visualizationcited by 0
  28. 2025A Data-Driven Interpolation Method on Smooth Manifolds via Diffusion Processes and Voronoi Tessellationscited by 0
  29. 2025The Tree-SNE Tree Existscited by 0
  30. 2025NexusFlow: Unifying Disparate Tasks under Partial Supervision via Invertible Flow Networkscited by 0
  31. 2026FENCE: A Financial and Multimodal Jailbreak Detection Datasetcited by 0
  32. 2026Leveraging Model Soups to Classify Intangible Cultural Heritage Images from the Mekong Deltacited by 0
  33. 2026Span Modeling for Idiomaticity and Figurative Language Detection with Span Contrastive Losscited by 0
  34. 2026A Spectral Decomposition Framework for Multiscale Nonlinear Dimensionality Reductioncited by 0
  35. 2026A Diffusion-Contrastive Graph Neural Network with Virtual Nodes for Wind Nowcasting in Unobserved Regionscited by 0
  36. 2026Heuristic Style Transfer for Real-Time, Efficient Weather Attribute Detectioncited by 0
  37. 2026Domain-Shift Aware Neural Networks for Unbalance Characterization in Rotating Systemscited by 0
  38. 2026A Controlled Benchmark of Quantum-Latent GAN Augmentation for Brain MRIcited by 0

50 most cited of 55 All 55 (JSON)