Functional Bregman Divergences

Overview

Functional Bregman divergences measure the gap between a convex functional at two objects and its first-order approximation, extending familiar vector divergences to functions, distributions, and model outputs. Approaches include Hilbert-space formulations with Riesz representers and kernel mean embeddings, as well as connections to Legendre and Fenchel–Young duality. The geometry supports applications such as kernel-based divergence estimation, online calibration with proper losses, decision-tree impurity design, alignment objectives, and optimization preconditioning. A central challenge is balancing useful asymmetry and task-specific geometry against tractable, statistically reliable estimation and performance that transfers across settings.

Latest papers

CardsList

10 papers1 paper in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

  1. The Bayesian Learning Rule Beyond KL Geometry

    Oct 22, 2026Sophia Sklaviadis, Wu Lin, Andre Martins +3Bayesian InferenceVariational Inference

  2. How Bregman Divergences Shape Shampoo

    Oct 6, 2026Bing Liu, Wenjie Zhou, Chengcheng Zhao +4Deep Learning OptimizationFunctional Bregman Divergences

  3. Role-Aware Neural Convex Divergence Heads for Asymmetric Representation Learning

    Jul 2, 2026He Huang, Lu Shen, Yunfeng Huang +1Representation LearningFunctional Bregman Divergences

  4. A Bregman Perspective on Classification and Regression Trees

    Jun 12, 2026Mathias BourelFunctional Bregman DivergencesDecision Tree Learning

  5. Calibeating for general proper losses: A Bregman divergence approach

    May 17, 2026Maximilian Fichtl, Cristóbal Guzmán, Nishant A. MehtaFunctional Bregman DivergencesProper Scoring Rules

  6. BSO: Safety Alignment Is Density Ratio Matching

    May 12, 2026Tien-Phat Nguyen, Truong Nguyen, Thin Nguyen +3Functional Bregman DivergencesDirect Preference Optimization

  7. Generalized Distributional Alignment Games for Unbiased Answer-Level Fine-Tuning

    May 4, 2026Mehryar Mohri, Jon Schneider, Yutao ZhongFine-TuningLLM Alignment

  8. Generalising maximum mean discrepancy: kernelised functional Bregman divergences

    Apr 27, 2026Russell Tsuchida, Frank NielsenKernel Mean EmbeddingsFunctional Bregman Divergences

  9. Quadratic polarity and polar Fenchel-Young divergences from the canonical Legendre polarity

    Mar 5, 2026Frank Nielsen, Basile Plus-Gourdon, Mahito SugiyamaInformation GeometryFunctional Bregman Divergences