Markov chain Phase-Type decoders in VAEs overcome the structural inability of Gaussian-Lipschitz models to produce heavy-tailed outputs, cutting tail KS distance by up to 6x and extreme quantile error by up to 10x on synthetic Pareto data.
arXiv preprint arXiv:2306.10987 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
stat.ML 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A survey of recent methods that apply extreme value theory to enable extrapolation in statistical learning and machine learning.
citing papers explorer
-
Markov Chain Decoders Overcome the Heavy-Tail Limitations of Lipschitz Generative Models
Markov chain Phase-Type decoders in VAEs overcome the structural inability of Gaussian-Lipschitz models to produce heavy-tailed outputs, cutting tail KS distance by up to 6x and extreme quantile error by up to 10x on synthetic Pareto data.
-
Extrapolation in Statistical Learning with Extreme Value Theory
A survey of recent methods that apply extreme value theory to enable extrapolation in statistical learning and machine learning.