Entropic Autoencoders mitigate posterior collapse by implicitly defining priors via entropy in a free-energy-minimizing encoder ensemble, yielding multimodal latent distributions that preserve data structure on reaction-diffusion, MNIST, and CelebA.
Sufficient is better than optimal for training neural networks.Nature Communications, 17(1):271, December 2025
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Entropy-based sampling of graph ensembles from simulated data quantifies causal structural ambiguity and reveals artifacts in single optimized DAGs.
citing papers explorer
-
Entropic Auto-Encoding via Implicit Free-Energy Minimization
Entropic Autoencoders mitigate posterior collapse by implicitly defining priors via entropy in a free-energy-minimizing encoder ensemble, yielding multimodal latent distributions that preserve data structure on reaction-diffusion, MNIST, and CelebA.
-
Causal Atlases from Entropic Inference: Bayesian Networks beyond Optimal DAGs
Entropy-based sampling of graph ensembles from simulated data quantifies causal structural ambiguity and reveals artifacts in single optimized DAGs.