ENFR recovers absolute Bayesian evidence using flow-matched references
Authors report better absolute-evidence estimates than a flow baseline and top density-estimation results on their benchmarks.
Stories per day · 30 days
2 RSS
Relatedbayesian-inference1evidence-estimation1image-generation1model-misspecification1simulation-based-inference1text-to-image1training-loss1vision-language1
3 stories, newest first · one card per story
Stories tagged #normalizing-flows
LILIE language-informed loss improves pixel-space text-to-image training
JiT models trained with LILIE cut GPIC gFD from 66.84 to 53.01 versus a pixel-only baseline.
Likelihood-free inference with nuisance parameters through normalizing flows
Researchers decompose normalizing flows to derive near-pivotal statistics for likelihood-free inference with nuisance parameters, recovering the t-test and beating Welch limits.