REVIEW 1 cited by
Dataset Dynamics via Gradient Flows in Probability Space
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
Signed reviews
read the original abstract
Various machine learning tasks, from generative modeling to domain adaptation, revolve around the concept of dataset transformation and manipulation. While various methods exist for transforming unlabeled datasets, principled methods to do so for labeled (e.g., classification) datasets are missing. In this work, we propose a novel framework for dataset transformation, which we cast as optimization over data-generating joint probability distributions. We approach this class of problems through Wasserstein gradient flows in probability space, and derive practical and efficient particle-based methods for a flexible but well-behaved class of objective functions. Through various experiments, we show that this framework can be used to impose constraints on classification datasets, adapt them for transfer learning, or to re-purpose fixed or black-box models to classify -- with high accuracy -- previously unseen datasets.
Forward citations
Cited by 1 Pith paper
-
A Dynamical Approximation Scheme on the Stiefel manifold for Wasserstein Gradient Flows
A Stiefel-manifold dynamical approximation for Wasserstein gradient flows represents the evolving transport map by a moving linear subspace and controls the Wasserstein error through an adaptive background space.
Discussion (0). Continue with ORCID to comment.