A novel generative modeling framework based on a discretized parabolic Monge–Ampère PDE emerges as a continuous limit of the Sinkhorn algorithm commonly used in optimal transport, and derives a new Evolution Variational Inequality tailored to the parabolic Monge–Ampère PDE.
Nabarun Deb, Tengyuan Liang· Annals of Statistics· 0 citations
This work studies the score learning error from finite data and derive optimal sampling guarantees with explicit dependence on the vocabulary size, the interaction order of the MRF, and the sample size, and trains a single score network across uniform noise levels while leaving the sampling discretization to be chosen...
The large deviation principle (LDP) is studied for a tensor-weighted functional of i.i.d. random variables, when the sequence of tensors converges under a variant of the"bad"cut norm, and sufficient conditions for uniqueness of the optimizer and existence of constant optimizers are given.
Reihaneh Malekian, Sohom Bhattacharya, Nabarun Deb et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.