REVIEW 1 cited by
Large data limits and scaling laws for tSNE
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
This work considers large-data asymptotics for t-distributed stochastic neighbor embedding (tSNE), a widely-used non-linear dimension reduction algorithm. We identify an appropriate continuum limit of the tSNE objective function, which can be viewed as a combination of a kernel-based repulsion and an asymptotically-vanishing Laplacian-type regularizer. As a consequence, we show that embeddings of the original tSNE algorithm cannot have any consistent limit as $n \to \infty$. We propose a rescaled model which mitigates the asymptotic decay of the attractive energy, and which does have a consistent limit.
Forward citations
Cited by 1 Pith paper
-
Equilibrium Distribution for t-Distributed Stochastic Neighbor Embedding with Generalized Kernels
Generalized t-SNE with radial exponential input kernels and integrable output kernels converges to a compactly supported equilibrium measure when perplexity scales as log(nρ).
Discussion (0). Continue with ORCID to comment.