Which dimensionality reduction technique minimizes the Kullback-Leibler divergence between similarity distributions in high and low-dimensional spaces?
Show answer
t-SNE
t-distributed Stochastic Neighbor Embedding (t-SNE) is highly effective at preserving local structure in data. It is widely used for visualizing high-dimensional clusters in two or three dimensions.
Also asked as:
- Which 2008 dimensionality reduction technique works by minimizing the KL divergence between similarity distributions in high and low-dimensional spaces?