Showing stat.MLShow all
2 papers · 1 filter
stat.ML2024
Operator-Informed Score Matching for Markov Diffusion Models
Zheyang Shen, Huihui Wang, Marina Riabiz +1
Diffusion models are typically trained using score matching, a learning objective agnostic to the underlying noising process that guides the model. This paper argues that Markov no…
stat.ML2020
Optimal quantisation of probability measures using maximum mean discrepancy
Onur Teymur, Jackson Gorham, Marina Riabiz +1
Several researchers have proposed minimisation of maximum mean discrepancy (MMD) as a method to quantise probability measures, i.e., to approximate a target distribution by a repre…