IA-VAE augments amortized variational inference with hypernetwork-generated instance-adaptive modulations, strictly containing the standard variational family and improving held-out ELBO on synthetic and image data.
Reducing the amortization gap in vari- ational autoencoders: A bayesian random function approach
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Instance-Adaptive Parametrization for Amortized Variational Inference
IA-VAE augments amortized variational inference with hypernetwork-generated instance-adaptive modulations, strictly containing the standard variational family and improving held-out ELBO on synthetic and image data.