EasyDeepLearn

UMAP key hyperparameters.

medium

Answer

  • (1) nneighborsn_{\mathrm{neighbors}}: local vs global (5-15 local, 50-100 global; default 15).
  • (2) min⁡dist\operatorname{min}_{\mathrm{dist}}: minimum spacing in embedding — small (0.1) preserves clusters, large (0.5) spreads points.
  • (3) ncomponentsn_{\mathrm{components}}: usually 2 for viz, 10-50 for downstream.
  • (4) metric: euclidean, cosine, correlation, hamming, custom callable.
  • (5) randomstate\mathrm{random}_{\mathrm{state}} for reproducibility.
  • Tune nneighbors  +  min⁡distn_{\mathrm{neighbors}}\; + \;\operatorname{min}_{\mathrm{dist}} together; try 3-4 combinations.
Check yourself — multiple choice
  • No parameters
  • nneighborsn_{\mathrm{neighbors}} (local/global), min⁡dist\operatorname{min}_{\mathrm{dist}} (cluster spacing), ncomponentsn_{\mathrm{components}}, metric; try 3-4 (nneighbors,  min⁡dist)(n_{\mathrm{neighbors}}, \;\operatorname{min}_{\mathrm{dist}}) combos
  • Same as t-SNE
  • Random

UMAP: nneighborsn_{\mathrm{neighbors}}, min⁡dist\operatorname{min}_{\mathrm{dist}}, ncomponentsn_{\mathrm{components}}, metric; tune first two.

#dimensionality-reduction#visualization

Practise Unsupervised Learning

214 interview questions in this topic.

Read the lessonFlashcardsTake the quiz

Related questions