中文
相关论文

相关论文: Pseudo-Riemannian geometry embeds information geom…

200 篇论文

Recent progress in geometric deep learning has drawn increasing attention from the machine learning community toward domain adaptation on symmetric positive definite (SPD) manifolds, especially for neuroimaging data that often suffer from…

机器学习 · 计算机科学 2025-05-09 Ce Ju , Cuntai Guan

The objective in statistical Optimal Transport (OT) is to consistently estimate the optimal transport plan/map solely using samples from the given source and target marginal distributions. This work takes the novel approach of posing…

机器学习 · 计算机科学 2020-11-11 J. Saketha Nath , Pratik Jawanpuria

This paper proposes an original Riemmanian geometry for low-rank structured elliptical models, i.e., when samples are elliptically distributed with a covariance matrix that has a low-rank plus identity structure. The considered geometry is…

The manifold of coupling constants parametrizing a quantum Hamiltonian is equipped with a natural Riemannian metric with an operational distinguishability content. We argue that the singularities of this metric are in correspondence with…

量子物理 · 物理学 2007-05-23 P. Zanardi , P. Giorda , M. Cozzini

Information geometry is a mathematical framework that elucidates the manifold structure of the probability distribution space (p-space), providing a systematic approach to transforming probability distributions (PDs). In this study, we…

数据分析、统计与概率 · 物理学 2025-06-30 Tomotaka Oroguchi , Rintaro Inoue , Masaaki Sugiyama

Understanding how neural population responses represent sensory information is a central problem in systems neuroscience. One approach is to define a representational geometry on stimulus space in which distances reflect how reliably…

神经元与认知 · 定量生物学 2026-05-08 Simone Azeglio , Steeve Laquitaine , Ulisse Ferrari , Matthew Chalk

We revisit the geometrical meaning of statistical isotropy that is manifest in excursion sets of smooth random fields in two dimensions. Using the contour Minkowski tensor, $\W_1$, as our basic tool we first examine geometrical properties…

宇宙学与河外天体物理 · 物理学 2021-12-15 Pravabati Chingangbam , Priya Goyal , K. P. Yogendran , Stephen Appleby

We introduce a novel geometric framework for optimal experimental design (OED). Traditional OED approaches, such as those based on mutual information, rely explicitly on probability densities, leading to restrictive invariance properties.…

机器学习 · 统计学 2025-10-17 Gavin Kerrigan , Christian A. Naesseth , Tom Rainforth

This paper is concerned by statistical inference problems from a data set whose elements may be modeled as random probability measures such as multiple histograms or point clouds. We propose to review recent contributions in statistics on…

统计理论 · 数学 2019-08-27 Jérémie Bigot

The primary objects of study in information geometry are statistical manifolds, which are parametrized families of probability measures, induced with the Fisher-Rao metric and a pair of torsion-free conjugate connections. In recent work,…

微分几何 · 数学 2023-05-02 Gabriel Khan , Jun Zhang

Upon a consistent topological statistical theory the application of structural statistics requires a quantification of the proximity structure of model spaces. An important tool to study these structures are Pseudo-Riemannian metrices,…

统计理论 · 数学 2020-06-23 Patrick Michl

Optimal transport (OT) distances are increasingly used as loss functions for statistical inference, notably in the learning of generative models or supervised learning. Yet, the behavior of minimum Wasserstein estimators is poorly…

统计理论 · 数学 2021-07-20 Tianyi Lin , Zeyu Zheng , Elynn Y. Chen , Marco Cuturi , Michael I. Jordan

Transportation of measure provides a versatile approach for modeling complex probability distributions, with applications in density estimation, Bayesian inference, generative modeling, and beyond. Monotone triangular transport…

机器学习 · 统计学 2024-02-27 Ricardo Baptista , Youssef Marzouk , Olivier Zahm

We illustrate how quantum information theory and free (i.e. noncommutative) semialgebraic geometry often study similar objects from different perspectives. We give examples in the context of positivity and separability, quantum magic…

量子物理 · 物理学 2024-03-05 Gemma De Las Cuevas , Tim Netzer

Information geometry promotes an investigation of the geometric structure of statistical manifolds, providing a series of elucidations in various areas of scientific knowledge. In the physical sciences, especially in quantum theory, this…

量子物理 · 物理学 2020-12-08 Gabriel F. Magno , Carlos H. Grossi , Gerardo Adesso , Diogo O. Soares-Pinto

Optimal transport (OT) has recently found widespread interest in machine learning. It allows to define novel distances between probability measures, which have shown promise in several applications. In this work, we discuss how to…

机器学习 · 计算机科学 2021-10-11 Bamdev Mishra , N T V Satyadev , Hiroyuki Kasai , Pratik Jawanpuria

Many natural and social science systems are described using probability distributions over elements that are related to each other: for instance, occupations with shared skills or species with similar traits. Standard information theory…

信息论 · 计算机科学 2026-03-24 Rohit Sahasrabuddhe , Renaud Lambiotte

We study a variant of the dynamical optimal transport problem in which the energy to be minimised is modulated by the covariance matrix of the distribution. Such transport metrics arise naturally in mean-field limits of certain ensemble…

偏微分方程分析 · 数学 2024-12-23 Martin Burger , Matthias Erbar , Franca Hoffmann , Daniel Matthes , André Schlichting

Optimal Transport has recently gained interest in machine learning for applications ranging from domain adaptation, sentence similarities to deep learning. Yet, its ability to capture frequently occurring structure beyond the "ground…

机器学习 · 统计学 2017-12-19 David Alvarez-Melis , Tommi S. Jaakkola , Stefanie Jegelka

We propose a new algorithm that uses an auxiliary neural network to express the potential of the optimal transport map between two data distributions. In the sequel, we use the aforementioned map to train generative networks. Unlike WGANs,…

机器学习 · 计算机科学 2020-04-21 Vaios Laschos , Jan Tinapp , Klaus Obermayer