Image de couverture de livre

Microcanonical Langevin Ensembles: Advancing the Sampling of Bayesian Neural Networks

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sommer, Emanuel, Robnik, Jakob, Nozadze, Giorgi, Seljak, Uros, Rügamer, David
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Can Microcanonical Langevin Dynamics Leverage Mini-Batch Gradient Noise?
par: Sommer, Emanuel, et autres
Publié: (2026)

Fluctuation without dissipation: Microcanonical Langevin Monte Carlo
par: Robnik, Jakob, et autres
Publié: (2023)

Metropolis Adjusted Microcanonical Hamiltonian Monte Carlo
par: Robnik, Jakob, et autres
Publié: (2025)

Position: The Time for Sampling Is Now! Charting a New Course for Bayesian Deep Learning
par: Sommer, Emanuel, et autres
Publié: (2026)

Microcanonical Hamiltonian Monte Carlo
par: Robnik, Jakob, et autres
Publié: (2022)

bde: A Python Package for Bayesian Deep Ensembles via MILE
par: Arvanitis, Vyron, et autres
Publié: (2026)

Radiological mapping and uncertainty quantification by a fast Microcanonical Langevin Monte Carlo sampler
par: Pan, Lei, et autres
Publié: (2026)

Towards E-Value Based Stopping Rules for Bayesian Deep Ensembles
par: Sommer, Emanuel, et autres
Publié: (2026)

Connecting the Dots: Is Mode-Connectedness the Key to Feasible Sample-Based Inference in Bayesian Neural Networks?
par: Sommer, Emanuel, et autres
Publié: (2024)

Reassessment of Kepler's habitable zone Earth-like exoplanets with data-driven null-signal templates
par: Robnik, Jakob, et autres
Publié: (2025)

Faster parallel MCMC: Metropolis adjustment is best served warm
par: Robnik, Jakob, et autres
Publié: (2026)

On the Interplay of Priors and Overparametrization in Bayesian Neural Network Posteriors
par: Kobialka, Julius, et autres
Publié: (2026)

Persistent Sampling: Enhancing the Efficiency of Sequential Monte Carlo
par: Karamanis, Minas, et autres
Publié: (2024)

Black-box unadjusted Hamiltonian Monte Carlo
par: Robnik, Jakob, et autres
Publié: (2024)

On the Epistemic Uncertainty of Overparametrized Neural Networks
par: Rügamer, David
Publié: (2026)

Paths and Ambient Spaces in Neural Loss Landscapes
par: Dold, Daniel, et autres
Publié: (2025)

Sequential Kalman Tuning of the $t$-preconditioned Crank-Nicolson algorithm: efficient, adaptive and gradient-free inference for Bayesian inverse problems
par: Grumitt, Richard D. P., et autres
Publié: (2024)

Multiscale Flow for Robust and Optimal Cosmological Analysis
par: Dai, Biwei, et autres
Publié: (2023)

Counterdiabatic Hamiltonian Monte Carlo
par: Cohn-Gordon, Reuben, et autres
Publié: (2026)

Exoplanet transit search at the detection limit: detection and false alarm vetting pipeline
par: Robnik, Jakob, et autres
Publié: (2026)

Rethinking Intrinsic Dimension Estimation in Neural Representations
par: Schulte, Rickmer, et autres
Publié: (2026)

Approximating Langevin Monte Carlo with ResNet-like Neural Network architectures
par: Miranda, Charles, et autres
Publié: (2023)

Reinforcement Learning for Microcanonical Graph Ensemble with Assortativity Constraints
par: Choi, Hoyun, et autres
Publié: (2026)

Scalable Higher-Order Tensor Product Spline Models
par: Rügamer, David
Publié: (2024)

Adaptive Stepsizing for Stochastic Gradient Langevin Dynamics in Bayesian Neural Networks
par: Rajpal, Rajit, et autres
Publié: (2025)

Sampling from Bayesian Neural Network Posteriors with Symmetric Minibatch Splitting Langevin Dynamics
par: Paulin, Daniel, et autres
Publié: (2024)

Bayesian Semi-structured Subspace Inference
par: Dold, Daniel, et autres
Publié: (2024)

Initial Conditions from Galaxies: Machine-Learning Subgrid Correction to Standard Reconstruction
par: Parker, Liam, et autres
Publié: (2025)

Uncertainty Quantification for Prior-Data Fitted Networks using Martingale Posteriors
par: Nagler, Thomas, et autres
Publié: (2025)

Repulsive Ensembles for Bayesian Inference in Physics-informed Neural Networks
par: Pilar, Philipp, et autres
Publié: (2025)

Post-Training Network Compression for 3D Medical Image Segmentation: Reducing Computational Efforts via Tucker Decomposition
par: Weber, Tobias, et autres
Publié: (2024)

Can Transformers Learn Full Bayesian Inference in Context?
par: Reuter, Arik, et autres
Publié: (2025)

Additive Model Boosting: New Insights and Path(ologie)s
par: Schulte, Rickmer, et autres
Publié: (2025)

Second Order Ensemble Langevin Method for Sampling and Inverse Problems
par: Liu, Ziming, et autres
Publié: (2022)

Controlled Langevin Dynamics for Sampling of Feedforward Neural Networks Trained with Minibatches
par: Zambon, Alessandro, et autres
Publié: (2026)

Inferring the Langevin Equation with Uncertainty via Bayesian Neural Networks
par: Bae, Youngkyoung, et autres
Publié: (2024)

Position: The Future of Bayesian Prediction Is Prior-Fitted
par: Müller, Samuel, et autres
Publié: (2025)

Constrained Ensemble Langevin Monte Carlo
par: Ding, Zhiyan, et autres
Publié: (2021)

Mean-Field Microcanonical Gradient Descent
par: Häggbom, Marcus, et autres
Publié: (2024)

Achieving interpretable machine learning by functional decomposition of black-box models into explainable predictor effects
par: Köhler, David, et autres
Publié: (2024)