Beyond Global Divergences: A Local-Mass Perspective on Bayesian Inference

arXiv:2606.27090 · stat.ML, cs.AI, cs.LG · Submitted 2026-06-25 · Read on arXiv

stat.ML, cs.AI, cs.LG

Submitted: 2026-06-25

Updated: 2026-10-02

Comments: 28 pages, 3 figures, 2 tables

Code: https://github.com/Forsythia0604/Local-Mass-Framework

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Calibration — 9× in this paper · explained in 9 episodes
• Bayesian Inference — 8× in this paper · explained in 6 episodes
• Absorb — 1× in this paper · explained in 1 episode
• Editor — 1× in this paper · explained in 2 episodes
• Fixed Point — 1× in this paper · explained in 2 episodes
• Generator — 1× in this paper · explained in 2 episodes
• Mode Collapse — 1× in this paper · explained in 2 episodes
• Monotonicity — 1× in this paper · explained in 2 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• Sufficiency — 1× in this paper · explained in 2 episodes
• Variational Bayes — 1× in this paper · explained in 2 episodes

Sources

• Auto-Encoding Variational Bayes
• Variational f-divergence Minimization

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• Scalable Posterior Uncertainty for Flexible Density-Based Clustering
• A Transport Geometry of Benign Overfitting
• Efficient quadratic entropy with distance sketches