PCA vs t-SNE vs UMAP — when do you use each?
mediumAnswer
- PCA is a linear, deterministic projection that preserves global variance — use it for compression, denoising, or as input to another model. t-SNE and UMAP are nonlinear and preserve local neighborhoods — use them for 2D/3D visualization, not for downstream modeling.
- UMAP is faster than t-SNE and preserves more global structure.
- Never interpret t-SNE distances between clusters as meaningful.
Check yourself — multiple choice
- t-SNE is the best choice for feeding into another model
- PCA is nonlinear; t-SNE is linear
- PCA for downstream ML, t-SNE/UMAP for visualization
- UMAP is slower than t-SNE
PCA is a linear tool used for modeling; t-SNE/UMAP are visualization tools.
#dimensionality-reduction#visualization
Practise Unsupervised Learning
214 interview questions in this topic.