The Ehresmann connection induced by the Fisher metric on the hierarchical parameter fiber bundle is flat for any smooth posterior, identifying the mixing obstruction as the prior fraction (pooling factor) rather than curvature.
Journal of Statistical Software , author=
21 Pith papers cite this work, alongside 7,378 external citations. Polarity classification is still indexing.
21
Pith papers citing it
7,378
external citations · OpenAlex
citation-role summary
background 1
baseline 1
citation-polarity summary
representative citing papers
EFE-based planning is formulated as variational free energy minimization with epistemic priors, decomposing into expected plan costs plus a complexity term.
Proper EFE-based planning is VFE plus planning and epistemic entropy corrections, realized by channel-reparameterized message passing that captures novelty.
ADELIA is the first AD-enabled INLA system that computes exact hyperparameter gradients via a structure-exploiting multi-GPU backward pass, delivering 4.2-7.9x per-gradient speedups and 5-8x better energy efficiency than finite differences on models with up to 1.9 million latent variables.
MSFAST extends the FAST FPCA method to multivariate sparse data via Bayesian modeling with orthonormal splines, standardization, Procrustes alignment, and efficient computation, yielding valid inferences especially in low signal-to-noise settings.
AD-HMC achieves geometric convergence in Wasserstein distance for HMC with general asymmetrical auxiliary momentum distributions by restoring self-adjointness via direction alternation, with extensions to leapfrog integrators.
A Bayesian hierarchical model integrates coherence penalization and level-specific focus into forecasting estimation, yielding improved predictive accuracy on simulated and Australian tourism data.
Bayesian joint model infers infectious virus shedding trajectories and derived infectiousness metrics from PCR and other proxies in SARS-CoV-2 using data from five cohorts of roughly 2000 infections.
RG-inspired lattice models for piecewise GLMs provide explicit interpretable partitions and a replica-analysis-derived scaling law for regularization that allows increasing complexity without expected rise in generalization loss.
DESI data on the GD-1 stream identifies a thin cold core and a hot cocoon with 30% of members whose dispersion is consistent with 11 Gyr of dark matter subhalo heating.
Probabilistic programs of thought let LLMs produce many program variants from one generation by building a compact probabilistic representation of the token distribution.
RefineStat improves small language model performance on probabilistic program synthesis by adding semantic constraint enforcement and diagnostic-aware refinement, producing syntactically and statistically reliable code that often matches larger models.
Two hybrid Bayesian surrogate training approaches integrate simulation and real-world data via a weighting strategy independent of surrogate family, shown in synthetic and real case studies to improve accuracy and diagnose simulation issues.
dynesty is an open-source Python package for dynamic nested sampling that improves efficiency in Bayesian posterior and evidence estimation compared to MCMC on certain problems.
Crab cues promote host-riding behavior in Lottia tenuisculpta while attachment to mobile hosts improves survival relative to fixed hosts.
StanBKT provides a unified Bayesian inference framework for BKT models supporting HMC, variational inference, and hierarchical variants, evaluated on ASSISTments and intervention datasets.
iLBA is an R package that combines small cell adjustment with controlled aggregation to produce confidential frequency tables from microdata.
A Dirichlet-based Bayesian forecasting model predicts the origin-country mix of Airbnb bookings and beats naive baselines for Europe, but not consistently across all regions.
GIGA-Lens 2.0 scales strong gravitational lens modeling across up to 128 GPU nodes and demonstrates it on 100 simulated systems plus one real DESI lens.
A within-participants study with design students found that sketch inputs to an AI ideation tool increased fluency but students still preferred text prompts, pointing to design choices that could better preserve reflective practice.
Union3 compilation of 2087 SNe Ia with UNITY1.5 framework shows 1.7-2.6 sigma tension with LambdaCDM and possible thawing dark energy.
citing papers explorer
-
A Flat Connection: The Pooling Factor and the Geometry of Centring in Hierarchical MCMC
The Ehresmann connection induced by the Fisher metric on the hierarchical parameter fiber bundle is flat for any smooth posterior, identifying the mixing obstruction as the prior fraction (pooling factor) rather than curvature.
-
Expected Free Energy-based Planning as Variational Inference
EFE-based planning is formulated as variational free energy minimization with epistemic priors, decomposing into expected plan costs plus a complexity term.
-
What Type of Inference is Active Inference?
Proper EFE-based planning is VFE plus planning and epistemic entropy corrections, realized by channel-reparameterized message passing that captures novelty.
-
ADELIA: Automatic Differentiation for Efficient Laplace Inference Approximations
ADELIA is the first AD-enabled INLA system that computes exact hyperparameter gradients via a structure-exploiting multi-GPU backward pass, delivering 4.2-7.9x per-gradient speedups and 5-8x better energy efficiency than finite differences on models with up to 1.9 million latent variables.
-
Bayesian Multivariate Sparse Functional Principal Components Analysis
MSFAST extends the FAST FPCA method to multivariate sparse data via Bayesian modeling with orthonormal splines, standardization, Procrustes alignment, and efficient computation, yielding valid inferences especially in low signal-to-noise settings.
-
Hamiltonian Monte Carlo with Asymmetrical Momentum Distributions
AD-HMC achieves geometric convergence in Wasserstein distance for HMC with general asymmetrical auxiliary momentum distributions by restoring self-adjointness via direction alternation, with extensions to leapfrog integrators.
-
Hierarchical Bayes meets hierarchical forecasting: A flexible framework for level-focused forecasts
A Bayesian hierarchical model integrates coherence penalization and level-specific focus into forecasting estimation, yielding improved predictive accuracy on simulated and Australian tourism data.
-
Inferring infectiousness: a joint model of the within-host viral kinetics of SARS-CoV-2
Bayesian joint model infers infectious virus shedding trajectories and derived infectiousness metrics from PCR and other proxies in SARS-CoV-2 using data from five cohorts of roughly 2000 infections.
-
A renormalization-group inspired lattice-based framework for piecewise generalized linear models
RG-inspired lattice models for piecewise GLMs provide explicit interpretable partitions and a replica-analysis-derived scaling law for regularization that allows increasing complexity without expected rise in generalization loss.
-
Characterizing the GD-1 Stream with DESI DR2 Data: Thin Stream and Hot Cocoon
DESI data on the GD-1 stream identifies a thin cold core and a hot cocoon with 30% of members whose dispersion is consistent with 11 Gyr of dark matter subhalo heating.
-
Probabilistic Programs of Thought
Probabilistic programs of thought let LLMs produce many program variants from one generation by building a compact probabilistic representation of the token distribution.
-
RefineStat: Efficient Exploration for Probabilistic Program Synthesis
RefineStat improves small language model performance on probabilistic program synthesis by adding semantic constraint enforcement and diagnostic-aware refinement, producing syntactically and statistically reliable code that often matches larger models.
-
Bayesian Surrogate Training on Multiple Data Sources: A Hybrid Modeling Strategy
Two hybrid Bayesian surrogate training approaches integrate simulation and real-world data via a weighting strategy independent of surrogate family, shown in synthetic and real case studies to improve accuracy and diagnose simulation issues.
-
dynesty: A Dynamic Nested Sampling Package for Estimating Bayesian Posteriors and Evidences
dynesty is an open-source Python package for dynamic nested sampling that improves efficiency in Bayesian posterior and evidence estimation compared to MCMC on certain problems.
-
Predator-associated cues promote host riding, and coupling to mobile hosts improves survival in an epizoic limpet
Crab cues promote host-riding behavior in Lottia tenuisculpta while attachment to mobile hosts improves survival relative to fixed hosts.
-
StanBKT: Rethinking Parameter Estimation in Bayesian Knowledge Tracing
StanBKT provides a unified Bayesian inference framework for BKT models supporting HMC, variational inference, and hierarchical variants, evaluated on ASSISTments and intervention datasets.
-
iLBA: An R package for confidentially disseminating aggregated frequency tables
iLBA is an R package that combines small cell adjustment with controlled aggregation to produce confidential frequency tables from microdata.
-
Forecasting the Evolving Composition of Inbound Tourism Demand: A Bayesian Compositional Time Series Approach Using Platform Booking Data
A Dirichlet-based Bayesian forecasting model predicts the origin-country mix of Airbnb bookings and beats naive baselines for Europe, but not consistently across all regions.
-
GIGA-Lens 2.0: Strong-Lens Modeling on Multiple GPU Nodes
GIGA-Lens 2.0 scales strong gravitational lens modeling across up to 128 GPU nodes and demonstrates it on 100 simulated systems plus one real DESI lens.
-
Reviving Reflection-in-Action: Instilling Designerly Thinking in AI-Supported Ideation through Multimodal Prompting
A within-participants study with design students found that sketch inputs to an AI ideation tool increased fluency but students still preferred text prompts, pointing to design choices that could better preserve reflective practice.
-
Union Through UNITY: Cosmology with 2,000 SNe Using a Unified Bayesian Framework
Union3 compilation of 2087 SNe Ia with UNITY1.5 framework shows 1.7-2.6 sigma tension with LambdaCDM and possible thawing dark energy.