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.
year 1992
8 Pith papers cite this work, alongside 4,377 external citations. Polarity classification is still indexing.
8
Pith papers citing it
4,377
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
PPAT residualizes losses via a prediction-powered control variate inside LURE, yielding lower-variance unbiased risk estimates, tailored acquisition, and asymptotic CIs that cover with fewer labels.
Laplace approximation framework for quantile regression with mixed-effects and Gaussian processes using Fisher information and population curvature of expected loss instead of observed Hessian.
Relative plausibility theory supplies a computational-level account of comparing explanations against evidence in legal proof, while probabilistic methods supply algorithmic-level implementations, and the two correspond when plausibility judgments meet basic coherence conditions.
Bayesian-ARGOS is a hybrid frequentist-Bayesian method that discovers equations from limited noisy observations more efficiently than SINDy or bootstrap-ARGOS while adding uncertainty quantification.
Mathematical analysis shows sparse linear regression mitigates output dimension collapse in brain-to-image reconstruction at small data scales by exploiting sparsity in the brain-to-feature mapping.
Introduces Laplace-approximated Bayesian PINNs for automatic loss-weight optimization when solving PDEs such as heat, wave, and Burgers equations.
Bayesian statistics supplies an automatic Occam's razor that penalizes unnatural models needing precise fine-tuning to agree with data, justifying naturalness arguments without aleatoric uncertainty.
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.
-
Prediction-Powered Active Testing
PPAT residualizes losses via a prediction-powered control variate inside LURE, yielding lower-variance unbiased risk estimates, tailored acquisition, and asymptotic CIs that cover with fewer labels.
-
Laplace Approximations for Mixed-Effects and Gaussian Process Quantile Regression
Laplace approximation framework for quantile regression with mixed-effects and Gaussian processes using Fisher information and population curvature of expected loss instead of observed Hessian.
-
Relative plausibility versus probabilism: A level-of-analysis error in juridical proof
Relative plausibility theory supplies a computational-level account of comparing explanations against evidence in legal proof, while probabilistic methods supply algorithmic-level implementations, and the two correspond when plausibility judgments meet basic coherence conditions.
-
Fast and principled equation discovery from chaos to climate
Bayesian-ARGOS is a hybrid frequentist-Bayesian method that discovers equations from limited noisy observations more efficiently than SINDy or bootstrap-ARGOS while adding uncertainty quantification.
-
Overcoming Output Dimension Collapse: When Sparsity Enables Zero-shot Brain-to-Image Reconstruction at Small Data Scales
Mathematical analysis shows sparse linear regression mitigates output dimension collapse in brain-to-image reconstruction at small data scales by exploiting sparsity in the brain-to-feature mapping.
-
Bayesian Reasoning for Physics Informed Neural Networks
Introduces Laplace-approximated Bayesian PINNs for automatic loss-weight optimization when solving PDEs such as heat, wave, and Burgers equations.
-
It's all in your head -- fine-tuning arguments do not require aleatoric uncertainty
Bayesian statistics supplies an automatic Occam's razor that penalizes unnatural models needing precise fine-tuning to agree with data, justifying naturalness arguments without aleatoric uncertainty.