t-SNE converges in the large-data limit to a non-convex variational energy with attraction and repulsion terms that admits a unique smooth minimizer but infinitely many discontinuous ones in one dimension.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
t-SNE loses important features of data in multiple scenarios, as formalized by new mathematical results.
citing papers explorer
-
On the continuum limit of t-SNE for data visualization
t-SNE converges in the large-data limit to a non-convex variational energy with attraction and repulsion terms that admits a unique smooth minimizer but infinitely many discontinuous ones in one dimension.
-
Some Theoretical Limitations of t-SNE
t-SNE loses important features of data in multiple scenarios, as formalized by new mathematical results.