paper-with-me

홈 › Papers

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

2026-03-05 · Frank Nielsen, Basile Plus-Gourdon, Mahito Sugiyama arxiv

Polarity is a fundamental reciprocal duality of $n$-dimensional projective geometry which associates to points polar hyperplanes, and more generally $k$-dimensional convex bodies to polar $(n-1-k)$-dimensional convex bodies. It is well-known that the Legendre-Fenchel transformation of functions can be interpreted from the polarity viewpoint of their graphs using an extra dimension. In this paper, we first show that generic polarities induced by quadratic polarity functionals can be expressed either as deformed Legendre polarity or as the Legendre polarity of deformed convex bodies, and be efficiently manipulated using linear algebra on $(n+2)\times (n+2)$ matrices operating on homogeneous coordinates. Second, we define polar divergences using the Legendre polarity and show that they generalize the Fenchel-Young divergence or equivalent Bregman divergence. This polarity study brings new understanding of the core reference duality in information geometry. Last, we show that the total Bregman divergences can be considered as a total polar Fenchel-Young divergence from which we newly exhibit the reference duality using dual polar conformal factors.

📄 PDF Abstract BibTeX arXiv:2603.04812

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Symplectic Bregman divergences

2024-08-23 · Frank Nielsen

We present a generalization of Bregman divergences in symplectic vector spaces that we term symplectic Bregman divergences. Symplectic Bregman divergences are derived from a symplectic generalization of the Fenchel-Young…

On change of measure inequalities for $f$-divergences

2022-02-11 · Antoine Picard-Weibel, Benjamin Guedj

We propose new change of measure inequalities based on $f$-divergences (of which the Kullback-Leibler divergence is a particular case). Our strategy relies on combining the Legendre transform of $f$-divergences and the Y…

Learning Classifiers with Fenchel-Young Losses: Generalized Entropies, Margins, and Algorithms

2018-05-24 · Mathieu Blondel, André F. T. Martins, Vlad Niculae

This paper studies Fenchel-Young losses, a generic way to construct convex loss functions from a regularization function. We analyze their properties in depth, showing that they unify many well-known loss functions and a…

Learning with Fitzpatrick Losses

2024-05-23 · Seta Rakotomandimby, Jean-Philippe Chancelier, Michel De Lara, Mathieu Blondel

Fenchel-Young losses are a family of convex loss functions, encompassing the squared, logistic and sparsemax losses, among others. Each Fenchel-Young loss is implicitly associated with a link function, for mapping model …

Sparse Continuous Distributions and Fenchel-Young Losses

2021-08-04 · André F. T. Martins, Marcos Treviso, António Farinhas, Pedro M. Q. Aguiar 외

Exponential families are widely used in machine learning, including many distributions in continuous and discrete domains (e.g., Gaussian, Dirichlet, Poisson, and categorical distributions via the softmax transformation)…

Audio ClassificationQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)