# t-SNE-CUDA: GPU-Accelerated t-SNE and its Applications to Modern Data

arXiv: https://arxiv.org/abs/1807.11824 · HTML: https://mlsanity.com/paper/1807.11824/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jul 2018.

## Built on by (most cited first, 19 of 19)

- [From t-SNE to UMAP with contrastive learning](https://mlsanity.com/paper/2206.01816/) (2022)
- [Unsupervised Continual Learning in Streaming Environments](https://mlsanity.com/paper/2109.09282/) (2021)
- [A Probabilistic Graph Coupling View of Dimension Reduction](https://mlsanity.com/paper/2201.13053/) (2022)
- [LoBAM: LoRA-Based Backdoor Attack on Model Merging](https://mlsanity.com/paper/2411.16746/) (2024)
- [DASH: Visual Analytics for Debiasing Image Classification via User-Driven Synthetic Data Augmentation](https://mlsanity.com/paper/2209.06357/) (2022)
- [IAN: Iterated Adaptive Neighborhoods for manifold learning and dimensionality estimation](https://mlsanity.com/paper/2208.09123/) (2022)
- [Deep Recursive Embedding for High-Dimensional Data](https://mlsanity.com/paper/2104.05171/) (2021)
- [cuSLINK: Single-linkage Agglomerative Clustering on the GPU](https://mlsanity.com/paper/2306.16354/) (2023)
- [Generalization Guarantees for Representation Learning via Data-Dependent Gaussian Mixture Priors](https://mlsanity.com/paper/2502.15540/) (2025)
- [SubOmiEmbed: Self-supervised Representation Learning of Multi-omics Data for Cancer Type Classification](https://mlsanity.com/paper/2202.01672/) (2022)
- [Self-omics: A Self-supervised Learning Framework for Multi-omics Cancer Data](https://mlsanity.com/paper/2210.00825/) (2022)
- [Advances in Electron Microscopy with Deep Learning](https://mlsanity.com/paper/2101.01178/) (2021)
- [Visualizing the embedding space to explain the effect of knowledge distillation](https://mlsanity.com/paper/2110.04483/) (2021)
- [Deep Recursive Embedding for High-Dimensional Data](https://mlsanity.com/paper/2111.00622/) (2021)
- [Scalable semi-supervised dimensionality reduction with GPU-accelerated EmbedSOM](https://mlsanity.com/paper/2201.00701/) (2022)
- [Accelerating Barnes-Hut t-SNE Algorithm by Efficient Parallelization on Multi-Core CPUs](https://mlsanity.com/paper/2212.11506/) (2022)
- [Out-of-Core Dimensionality Reduction for Large Data via Out-of-Sample Extensions](https://mlsanity.com/paper/2408.04129/) (2024)
- [The Confusion is Real: GRAPHIC -- A Network Science Approach to Confusion Matrices in Deep Learning](https://mlsanity.com/paper/2602.19770/) (2026)
- [A Multi-Attribute Latent Space for Visual Analysis of Watches](https://mlsanity.com/paper/2606.27897/) (2026)

## Abstract (arXiv)

Modern datasets and models are notoriously difficult to explore and analyze due to their inherent high dimensionality and massive numbers of samples. Existing visualization methods which employ dimensionality reduction to two or three dimensions are often inefficient and/or ineffective for these datasets. This paper introduces t-SNE-CUDA, a GPU-accelerated implementation of t-distributed Symmetric Neighbor Embedding (t-SNE) for visualizing datasets and models. t-SNE-CUDA significantly outperforms current implementations with 50-700x speedups on the CIFAR-10 and MNIST datasets. These speedups enable, for the first time, visualization of the neural network activations on the entire ImageNet dataset - a feat that was previously computationally intractable. We also demonstrate visualization performance in the NLP domain by visualizing the GloVe embedding vectors. From these visualizations, we can draw interesting conclusions about using the L2 metric in these embedding spaces. t-SNE-CUDA is publicly available athttps://github.com/CannyLab/tsne-cuda