Barycenter models, based on stochastic and deterministic optimal transport bridges between probability measures, have proven to be useful for supervised and unsupervised learning for (probability) measure-valued data. In this paper, we utilize the directional asymmetry and dual drift-diffusion control arising in the re...
Ngoc-Hai Nguyen, Thuan Nguyen, Prakash Ishwar et al.· 0 citations
A novel multi-marginal (MM) inverse OT (IOT) contrastive learning (CL) approach called Neg-MMIOT-CL is developed, which learns representations such that the global multi-marginal OT (MMOT) coupling between a triple of data marginals, with respect to a carefully designed ground-cost between triplets of data points in th...
Ngoc-Hai Nguyen, Thuan Nguyen, Prakash Ishwar et al.· 0 citations
Geometry-Spectral Rectification (GSR), a theoretically grounded framework that treats long-tailed learning as a spectral regularization problem, is proposed, offering a superior trade-off between computational efficiency and robust generalization in long-tailed settings.
Q. Tran, Ngoc-Hai Nguyen, Quan Dao et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.