English
Related papers

Related papers: K\"ahlerian information geometry for signal proces…

200 papers

We study Hermitian metrics with a Gauduchon connection being "K\"ahler-like", namely, satisfying the same symmetries for curvature as the Levi-Civita and Chern connections. In particular, we investigate $6$-dimensional solvmanifolds with…

Differential Geometry · Mathematics 2023-03-21 Daniele Angella , Antonio Otal , Luis Ugarte , Raquel Villacampa

Let (M,g) be a compact, connected and oriented Riemannian manifold. We denote D the space of smooth probability density functions on M. In this paper, we show that the Frechet manifold D is equipped with a Riemannian metric g^{D} and an…

Differential Geometry · Mathematics 2012-04-04 Mathieu Molitor

Research on the use of information geometry (IG) in modern physics has witnessed significant advances recently. In this review article, we report on the utilization of IG methods to define measures of complexity in both classical and,…

Statistical Mechanics · Physics 2018-04-10 D. Felice , C. Cafaro , S. Mancini

In signal processing, a signal is a function. Conceptually, replacing a function by its graph, and extending this approach to a more abstract setting, we define a signal as a submanifold M of a Riemannian manifold (with corners) that…

Differential Geometry · Mathematics 2024-08-26 Tatyana Barron

We consider K\"ahler toric manifolds $N$ that are torifications of statistical manifolds $\mathcal{E}$ in the sense of [M. Molitor, "K\"ahler toric manifolds from dually flat spaces", arXiv:2109.04839], and prove a geometric analogue of the…

Differential Geometry · Mathematics 2023-05-18 Mathieu Molitor

By restricting the iterate on a nonlinear manifold, the recently proposed Riemannian optimization methods prove to be both efficient and effective in low rank tensor completion problems. However, existing methods fail to exploit the easily…

Machine Learning · Statistics 2017-02-24 Tengfei Zhou , Hui Qian , Zebang Shen , Congfu Xu

We show that every Kaehler algebraic curvature tensor is geometrically realizable by a Kaehler manifold of constant scalar curvature. We also show that every para-Kaehler algebraic curvature tensor is geometrically realizable by a…

Differential Geometry · Mathematics 2015-05-14 M. Brozos-Vazquez , P. Gilkey , E. Merino

Spectral compressed sensing involves reconstructing a spectral-sparse signal from a subset of uniformly spaced samples, with applications in radar imaging and wireless channel estimation. By fully exploiting the signal structures, this…

Optimization and Control · Mathematics 2025-11-25 Wenlong Wang , Wen Huang , Zai Yang

The Fisher information metric is an important foundation of information geometry, wherein it allows us to approximate the local geometry of a probability distribution. Recurrent neural networks such as the Sequence-to-Sequence (Seq2Seq)…

Machine Learning · Statistics 2018-01-09 Alessandro Bay , Biswa Sengupta

In this work, we develop an optimization framework for problems whose solutions are well-approximated by Hierarchical Tucker (HT) tensors, an efficient structured tensor format based on recursive subspace factorizations. By exploiting the…

Numerical Analysis · Mathematics 2014-05-12 Curt Da Silva , Felix J. Herrmann

We prove that every projective special K\"ahler manifold with \emph{regular boundary behaviour} is complete and defines a family of complete quaternionic K\"ahler manifolds depending on a parameter $c\ge 0$. We also show that, irrespective…

Differential Geometry · Mathematics 2016-12-30 Vicente Cortés , Malte Dyckmanns , Stefan Suhr

We examine phase transition of the Husimi-Temperley model in terms of information geometry. For this purpose, we introduce the Fisher metric defined by the density matrix of the model. We find that the metric becomes hyperbolic at the…

Statistical Mechanics · Physics 2014-07-11 Yoichiro Hashizume , Hiroaki Matsueda

This paper presents the computational methods of information cohomology applied to genetic expression in and in the companion paper and proposes its interpretations in terms of statistical physics and machine learning. In order to further…

Neurons and Cognition · Quantitative Biology 2019-07-16 Pierre Baudot

We consider strict and complete nearly Kaehler manifolds with the canonical Hermitian connection. The holonomy representation of the canonical Hermitian connection is studied. We show that a strict and complete nearly Kaehler is locally a…

Differential Geometry · Mathematics 2007-05-23 Paul-Andi Nagy

The K\"ahler cone of a compact K\"ahler manifold carries a natural Riemannian metric, given by the intersection product of its cohomology ring. We give cohomological expressions for the Levi-Civita connection and curvature tensor of this…

Algebraic Geometry · Mathematics 2020-04-16 Gunnar Þór Magnússon

The kernel least mean squares (KLMS) algorithm is a computationally efficient nonlinear adaptive filtering method that "kernelizes" the celebrated (linear) least mean squares algorithm. We demonstrate that the least mean squares algorithm…

Machine Learning · Statistics 2013-10-22 Il Memming Park , Sohan Seth , Steven Van Vaerenbergh

Information Geometry generalizes to infinite dimension by modeling the tangent space of the relevant manifold of probability densities with exponential Orlicz spaces. We review here several properties of the exponential manifold on a…

Statistics Theory · Mathematics 2023-07-19 Bertrand Lods , Giovanni Pistone

We propose a unified information-geometric framework that formalizes understanding in learning as a trade-off between informativeness and geometric simplicity. An encoder phi is evaluated by U(phi) = I(phi(X); Y) - beta * C(phi), where…

Machine Learning · Computer Science 2025-11-05 Ronald Katende

We study equivalence of invariant metrics on noncompact K\"ahler manifolds with a complete Bergman metric of bounded curvature. Especially only the boundedness of the ratio between Bergman kernel and the $n$-times wedge product of Bergman…

Differential Geometry · Mathematics 2023-12-04 Gunhee Cho , Kyu-Hwan Lee

The goal of tensor completion is to fill in missing entries of a partially known tensor (possibly including some noise) under a low-rank constraint. This may be formulated as a least-squares problem. The set of tensors of a given…

Numerical Analysis · Mathematics 2018-12-03 Gennadij Heidel , Volker Schulz