A JEPA-based hypernetwork maps lattice field theory couplings to flow-model weights, and the geometry of those weights recovers the phase transition, intrinsic dimension, and Ising critical exponent of 2D scalar field theory without supervised physics labels.
Bayesian Hypernetworks
6 Pith papers cite this work. Polarity classification is still indexing.
6
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
roles
method 1polarities
use method 1representative citing papers
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 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.
Frontier LLMs' self-declared language support is unstable and over-optimistic, verified behavior is task-dependent, and language mismatch alone degrades collaborative agent performance.
DAPPr projects a possibilistic posterior over network parameters to predictions using supremum operators and approximates it with learnable Dirichlet functions to yield an efficient training objective for epistemic uncertainty.
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.
citing papers explorer
-
Weight-Space Physics: Interpretable Hypernetworks for Lattice Quantum Field Theories
A JEPA-based hypernetwork maps lattice field theory couplings to flow-model weights, and the geometry of those weights recovers the phase transition, intrinsic dimension, and Ising critical exponent of 2D scalar field theory without supervised physics labels.
-
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.
-
Lost in the Tower of Babel: The Adverse Effects of Incidental Multilingualism in LLMs
Frontier LLMs' self-declared language support is unstable and over-optimistic, verified behavior is task-dependent, and language mismatch alone degrades collaborative agent performance.
-
Possibilistic Predictive Uncertainty for Deep Learning
DAPPr projects a possibilistic posterior over network parameters to predictions using supremum operators and approximates it with learnable Dirichlet functions to yield an efficient training objective for epistemic uncertainty.
-
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.