Dataset Dynamics via Gradient Flows in Probability Space

Understand

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.