English
Related papers

Related papers: Projections with logarithmic divergences

200 papers

We obtain new two-sided norm estimates for the family of Bergman-type projections arising from the standard weights $(1-|z|^2)^{\alpha}$ where $\alpha>-1$. As $\alpha\to -1$, the lower bound is sharp in the sense that it asymptotically…

Complex Variables · Mathematics 2017-01-10 Congwen Liu , Antti Perälä , Lifang Zhou

Bregman proximal point algorithm (BPPA) has witnessed emerging machine learning applications, yet its theoretical understanding has been largely unexplored. We study the computational properties of BPPA through learning linear classifiers…

Machine Learning · Computer Science 2023-08-28 Yan Li , Caleb Ju , Ethan X. Fang , Tuo Zhao

We define a metric and a family of $\alpha$-connections in statistical manifolds, based on $\varphi$-divergence, which emerges in the framework of $\varphi$-families of probability distributions. This metric and $\alpha$-connections…

Probability · Mathematics 2015-11-05 Rui F. Vigelis , David C. de Souza , Charles C. Cavalcante

We derive the information geometry induced by the statistical R\'enyi divergence, namely its metric tensor, its dual parametrized connections, as well as its dual Laplacians. Based on these results, we demonstrate that the R\'enyi-geometry,…

Statistics Theory · Mathematics 2025-06-17 Rebecca Maria Kuntz , Heinrich von Campe , Björn Malte Schäfer

By analogy to the terminology of curved exponential families in statistics, we define curved Bregman divergences as Bregman divergences restricted to non-affine parameter subspaces and sub-dimensional Bregman divergences when the…

Information Theory · Computer Science 2026-03-30 Frank Nielsen

For $\alpha>0$, the Bargmann projection $P_\alpha$ is the orthogonal projection from $L^2(\gamma_\alpha)$ onto the holomorphic subspace $L^2_{hol}(\gamma_\alpha)$, where $\gamma_\alpha$ is the standard Gaussian probability measure on $\C^n$…

Functional Analysis · Mathematics 2012-11-27 William E. Gryc , Todd Kemp

There is growing interest in using the close connection between differential geometry and statistics to model smooth manifold-valued data. In particular, much work has been done recently to generalize principal component analysis (PCA), the…

Other Statistics · Statistics 2016-10-07 Drew Lazar , Lizhen Lin

The dually flat structure introduced by Amari-Nagaoka is highlighted in information geometry and related fields. In practical applications, however, the underlying pseudo-Riemannian metric may often be degenerate, and such an excellent…

Differential Geometry · Mathematics 2021-03-26 Naomichi Nakajima , Toru Ohmoto

Jae-Suk Park and the second-named author introduce the deformation problem of coisotropic submanifolds of a symplectic manifold as the study of Mauer-Cartan moduli problem of an $L_\infty$ algebra attached to the foliation de-Rham complex…

Symplectic Geometry · Mathematics 2026-03-03 Taesu Kim , Yong-Geun Oh

Algebraic dichotomy is a generalization of an exponential dichotomy (Lin, JDE2009). This paper gives a version of Hartman-Grobman linearization theorem assuming that linear system admits an algebraic dichotomy, which generalizes the…

Classical Analysis and ODEs · Mathematics 2023-06-16 Chaofan Pan , Manuel Pinto , Y. H. Xia

We study the geometry of probability distributions with respect to a generalized family of Csisz\'ar $f$-divergences. A member of this family is the relative $\alpha$-entropy which is also a R\'enyi analog of relative entropy in information…

Information Theory · Computer Science 2020-05-26 M. Ashok Kumar , Kumar Vijay Mishra

In this paper, we expand the foundations of derived complex analytic geometry introduced in [DAG-IX] by J. Lurie. We start by studying the analytification functor and its properties. In particular, we prove that for a derived complex scheme…

Algebraic Geometry · Mathematics 2018-12-27 Mauro Porta

We investigate the construction of exponential families from statistical manifolds, a central problem in information geometry. We prove that every compact statistical manifold admits a singular foliation whose leaves are Hessian manifolds.…

Differential Geometry · Mathematics 2026-02-20 Emmanuel Gnandi

Fluctuation geometry was recently proposed as a counterpart approach of Riemannian geometry of inference theory. This theory describes the geometric features of the statistical manifold $\mathcal{M}$ of random events that are described by a…

Mathematical Physics · Physics 2016-02-24 L. Velazquez

In this paper, we introduce a new class of Bregman generalized $\alpha$-nonexpansive mappings in terms of Bregman distances, and investigate the Ishikawa and Noor iterations for these mappings. We establish weak and strong convergence…

Functional Analysis · Mathematics 2018-11-30 K. Muangchoo , P. Kumam , Y. J. Cho , S. Dhompongsa

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…

Computational Geometry · Computer Science 2026-03-06 Frank Nielsen , Basile Plus-Gourdon , Mahito Sugiyama

In Part I of this article we generalize the Linearized Doubling (LD) approach, introduced in earlier work by NK, by proving a general theorem stating that if $\Sigma$ is a closed minimal surface embedded in a Riemannian three-manifold…

Differential Geometry · Mathematics 2022-12-06 Nikolaos Kapouleas , Peter McGrath

We prove a duality theorem the computation of certain Bellman functions is usually based on. As a byproduct, we obtain sharp results about the norms of monotonic rearrangements. The main novelty of our approach is a special class of…

Optimization and Control · Mathematics 2016-04-07 Dmitriy M. Stolyarov , Pavel B. Zatitskiy

The last two decades, since the seminal work of Selig, has seen projective geometric algebra (PGA) gain popularity as a modern coordinate-free framework for doing classical Euclidean geometry and other Cayley-Klein geometries. This…

Rings and Algebras · Mathematics 2024-12-13 John Bamberg , Jeff Saunders

We propose a new family of regularized R\'enyi divergences parametrized not only by the order $\alpha$ but also by a variational function space. These new objects are defined by taking the infimal convolution of the standard R\'enyi…

Machine Learning · Statistics 2023-02-16 Jeremiah Birrell , Yannis Pantazis , Paul Dupuis , Markos A. Katsoulakis , Luc Rey-Bellet