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.
Bayesian hypernetworks
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
We study Bayesian hypernetworks: a framework for approximate Bayesian inference in neural networks. A Bayesian hypernetwork $\h$ is a neural network which learns to transform a simple noise distribution, $p(\vec\epsilon) = \N(\vec 0,\mat I)$, to a distribution $q(\pp) := q(h(\vec\epsilon))$ over the parameters $\pp$ of another neural network (the "primary network")\@. We train $q$ with variational inference, using an invertible $\h$ to enable efficient estimation of the variational lower bound on the posterior $p(\pp | \D)$ via sampling. In contrast to most methods for Bayesian deep learning, Bayesian hypernets can represent a complex multimodal approximate posterior with correlations between parameters, while enabling cheap iid sampling of~$q(\pp)$. In practice, Bayesian hypernets can provide a better defense against adversarial examples than dropout, and also exhibit competitive performance on a suite of tasks which evaluate model uncertainty, including regularization, active learning, and anomaly detection.
citation-role summary
method 1
citation-polarity summary
verdicts
UNVERDICTED 5roles
method 1polarities
use method 1representative citing papers
U-FaceBP combines multiple Bayesian neural networks in an ensemble to estimate blood pressure from face video modalities while quantifying uncertainty, showing improved performance on datasets with 1197 diverse subjects.
DAPPr introduces a possibilistic framework that projects parameter posteriors to predictions via supremum and approximates them with Dirichlet possibility functions to yield efficient, closed-form epistemic uncertainty estimates.
HyperFitS is a hypernetwork for configurable spectral fitting in 1H MRSI that matches conventional LCModel results while processing whole-brain data in seconds instead of hours and adapting to varied protocols without retraining.
Incidental multilingualism from uneven web training makes LLMs unequal, brittle, and opaque across languages.
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.
-
U-FaceBP: Uncertainty-aware Bayesian Ensemble Deep Learning for Face Video-based Blood Pressure Estimation
U-FaceBP combines multiple Bayesian neural networks in an ensemble to estimate blood pressure from face video modalities while quantifying uncertainty, showing improved performance on datasets with 1197 diverse subjects.
-
Possibilistic Predictive Uncertainty for Deep Learning
DAPPr introduces a possibilistic framework that projects parameter posteriors to predictions via supremum and approximates them with Dirichlet possibility functions to yield efficient, closed-form epistemic uncertainty estimates.
-
HyperFitS -- Hypernetwork Fitting Spectra for metabolic quantification of ${}^1$H MR spectroscopic imaging
HyperFitS is a hypernetwork for configurable spectral fitting in 1H MRSI that matches conventional LCModel results while processing whole-brain data in seconds instead of hours and adapting to varied protocols without retraining.
-
Lost in the Tower of Babel: The Adverse Effects of Incidental Multilingualism in LLMs
Incidental multilingualism from uneven web training makes LLMs unequal, brittle, and opaque across languages.