aiqbench analysis
DR-SNE introduces a density-regularization technique to Stochastic Neighbor Embedding, addressing known distortions in local data distributions during dimensionality reduction. By aligning neighborhood-scale profiles between original and embedded spaces, this method offers a more faithful representation of relative local concentrations without sacrificing neighborhood fidelity. This advancement is particularly relevant for researchers developing high-fidelity visualizations and representations where preserving specific data density variations is critical.
DR-SNE: Density-Regularized Stochastic Neighbor Embedding
arXiv:2605.02060v2 Announce Type: replace Abstract: Dimensionality-reduction methods such as t-SNE preserve local neighborhood structure but can substantially distort the local distribution of data. We introduce Density-Regularized Stochastic Neighbor Embedding (DR-SNE), which augments stochastic neighbor embedding with a regularizer that directly aligns normalized inverse-neighborhood-scale profiles between the original and embedding spaces. The resulting objective preserves relative local concentration while remaining invariant to global rescaling of the embedding. Across real and synthetic datasets, DR-SNE generally improves preservation of the targeted concentration profile while maintaining controlled levels of neighborhood fidelity. Experiments reveal a consistent empirical trade-off between concentration preservation and neighborhood fidelity as the regularization strength varies. These results position DR-SNE as a simple extension of SNE for settings in which relative variation in local concentration is an important property of the representation.
Abstract:Dimensionality-reduction methods such as t-SNE preserve local neighborhood structure but can substantially distort the local distribution of data. We introduce Density-Regularized Stochastic Neighbor Embedding (DR-SNE), which augments stochastic neighbor embedding with a regularizer that directly aligns normalized inverse-neighborhood-scale profiles between the original and embedding spaces. The resulting objective preserves relative local concentration while remaining invariant to global rescaling of the embedding. Across real and synthetic datasets, DR-SNE generally improves preservation of the targeted concentration profile while maintaining controlled levels of neighborhood fidelity. Experiments reveal a consistent empirical trade-off between concentration preservation and neighborhood fidelity as the regularization strength varies. These results position DR-SNE as a simple extension of SNE for settings in which relative variation in local concentration is an important property of the representation.
Machine Learning (cs.LG)
arXiv:2605.02060 [cs.LG]
(or arXiv:2605.02060v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2605.02060 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 217 words
Related coverage
Verifiable Regularity Criterion for Conditional Expectation Operators and Conditional Mean Embeddings with Applications to Nonparametric Regression, Bayesian Inverse Problems, and Koopman Operators
arXiv · Aug 7, 2026
Equilibrium Distribution for t-Distributed Stochastic Neighbor Embedding with Generalized Kernels
arXiv · Oct 9, 2026
Improved convergence rate of kNN graph Laplacians: differentiable self-tuned affinity
arXiv · Aug 4, 2026
Quantum annealer finds ground states of complex magnetic lattices
Quantum Zeitgeist · Sep 2, 2026