Parameter Estimation for Unnormalized Discrete Models via Empirically Localized Deformed Bregman Divergence

arXiv:2609.30713 · stat.ML, cs.LG · Submitted 2026-09-25 · Read on arXiv

stat.ML, cs.LG

Submitted: 2026-09-25

Updated: 2026-09-25

Terminology

• Robustness — 13× in this paper · explained in 5 episodes
• Contrastive Divergence — 6× in this paper
• Consistency — 4× in this paper · explained in 3 episodes
• Minimum Probability Flow — 3× in this paper
• Fisher Information — 2× in this paper · explained in 3 episodes
• Flow Matching — 2× in this paper · explained in 8 episodes
• Generative Modeling — 2× in this paper · explained in 3 episodes
• Bayesian-like Maximum A Posteriori — 1× in this paper
• Generalization — 1× in this paper · explained in 13 episodes
• Geometric Distribution — 1× in this paper · explained in 2 episodes
• Influence Functions — 1× in this paper · explained in 2 episodes
• Langevin Dynamics — 1× in this paper · explained in 2 episodes
• Markov Chain Monte Carlo — 1× in this paper

Sources

• Bregman divergence as general framework to estimate unnormalized statistical models
• Interpretation and Generalization of Score Matching

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
• Efficient quadratic entropy with distance sketches
• Embedding-Bias in Conditional Independence Testing
• From Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier