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

2026-06-25 · Hanli Xu, Fengxiang He, Sarat Moka arxiv

Global objectives, such as KL divergence and ELBO, are widely used in Bayesian inference for measuring distributional discrepancy. This paper studies their local-mass behaviour that is not directly captured by such objectives. We introduce and use two mathematical tools: (1) Mass Index for recording the polynomial and logarithmic decay scales of local mass, and (2) regularised extended KL (RE-KL), a set-localised divergence that can be formulated in the presence of singular components. Mass Indices help characterise how Bayesian updating changes local mass: (1) power-log likelihood factors shift it explicitly, and (2) parameter-dependent supports, or their smooth softenings, may change the local scale through the amount of mass that remains near the parameter value. Using local RE-KL, we prove absolute, relative, and directional inequalities for comparing local small-ball masses under the two KL directions. Together, these results provide a local theoretical account of local mass behaviour. Experiments provide controlled illustrations of the local behaviour. Code is available at https://github.com/Forsythia0604/Local-Mass-Framework.

📄 PDF Abstract BibTeX arXiv:2606.27090

Code (0)

등록된 구현이 없습니다.

Tasks

Bayesian Inference

$(f,Γ)$-Divergences: Interpolating between $f$-Divergences and Integral Probability Metrics

2020-11-11 · Jeremiah Birrell, Paul Dupuis, Markos A. Katsoulakis, Yannis Pantazis 외

We develop a rigorous and general framework for constructing information-theoretic divergences that subsume both $f$-divergences and integral probability metrics (IPMs), such as the $1$-Wasserstein distance. We prove und…

Image Generation Uncertainty Quantification

Variational Inference with Tail-adaptive f-Divergence

2018-10-29 · NeurIPS 2018 12 · Dilin Wang, Hao liu, Qiang Liu

Variational inference with {\alpha}-divergences has been widely used in modern probabilistic machine learning. Compared to Kullback-Leibler (KL) divergence, a major advantage of using {\alpha}-divergences (with positive …

Deep Reinforcement Learning Reinforcement Learning Variational Inference

Evaluating Bregman Divergences for Probability Learning from Crowd

2019-01-30 · F. A. Mena, R. Ñanculef

The crowdsourcing scenarios are a good example of having a probability distribution over some categories showing what the people in a global perspective thinks. Learn a predictive model of this probability distribution c…

Demystifying Why Local Aggregation Helps: Convergence Analysis of Hierarchical SGD

2020-10-24 · Jiayi Wang, Shiqiang Wang, Rong-Rong Chen, Mingyue Ji

Hierarchical SGD (H-SGD) has emerged as a new distributed SGD algorithm for multi-level communication networks. In H-SGD, before each global aggregation, workers send their updated local models to local servers for aggre…

Federated Learning

Local and Global Contraction Principles for MCMC Mixing

2026-06-02 · Alireza Daeijavad, Shahab Asoodeh arxiv

We develop a contraction-based framework for proving mixing-time bounds for Markov chain Monte Carlo algorithms. The framework is built around global and local contraction coefficients of Markov kernels under the $\maths…