English
Related papers

Related papers: Approximation and bounding techniques for the Fish…

200 papers

Recently proposed methods in data subset selection, that is active learning and active sampling, use Fisher information, Hessians, similarity matrices based on gradients, and gradient lengths to estimate how informative data is for a…

Machine Learning · Computer Science 2022-11-08 Andreas Kirsch , Yarin Gal

The Wasserstein distance is a distance between two probability distributions and has recently gained increasing popularity in statistics and machine learning, owing to its attractive properties. One important approach to extending this…

Methodology · Statistics 2022-02-14 Ryo Okano , Masaaki Imaizumi

Uncertainty propagation and filtering can be interpreted as gradient flows with respect to suitable metrics in the infinite dimensional manifold of probability density functions. Such a viewpoint has been put forth in recent literature, and…

Optimization and Control · Mathematics 2017-10-31 Abhishek Halder , Tryphon T. Georgiou

This work presents an explicit description of the Fisher-Rao Riemannian metric on the Hilbert manifold of equivalent centered Gaussian measures on an infinite-dimensional Hilbert space. We show that the corresponding quantities from the…

Probability · Mathematics 2023-10-17 Minh Ha Quang

I define a natural measure of the complexity of a parametric distribution relative to a given true distribution called the {\it razor} of a model family. The Minimum Description Length principle (MDL) and Bayesian inference are shown to…

adap-org · Physics 2008-02-03 Vijay Balasubramanian

Laplace's method approximates a target density with a Gaussian distribution at its mode. It is computationally efficient and asymptotically exact for Bayesian inference due to the Bernstein-von Mises theorem, but for complex targets and…

Machine Learning · Computer Science 2026-03-12 Hanlin Yu , Marcelo Hartmann , Bernardo Williams , Mark Girolami , Arto Klami

This paper introduces a comprehensive framework to adjust a discrete test statistic for improving its hypothesis testing procedure. The adjustment minimizes the Wasserstein distance to a null-approximating continuous distribution, tackling…

Statistics Theory · Mathematics 2025-06-13 Gonzalo Contador , Zheyang Wu

This paper presents a novel method for analyzing the latent space geometry of generative models, including statistical physics models and diffusion models, by reconstructing the Fisher information metric. The method approximates the…

Machine Learning · Computer Science 2025-06-13 Alexander Lobashev , Dmitry Guskov , Maria Larchenko , Mikhail Tamm

In information geometry, statistical models are considered as differentiable manifolds, where each probability distribution represents a unique point on the manifold. A Riemannian metric can be systematically obtained from a divergence…

Statistics Theory · Mathematics 2025-07-29 Satyajit Dhadumia , M. Ashok Kumar

Supervised dimensionality reduction maps labeled data into a low-dimensional feature space while preserving class discriminability. A common approach is to maximize a statistical measure of dissimilarity between classes in the feature…

Machine Learning · Statistics 2025-11-03 Daniel Herrera-Esposito , Johannes Burge

A new Riemannian geometry for the Compound Gaussian distribution is proposed. In particular, the Fisher information metric is obtained, along with corresponding geodesics and distance function. This new geometry is applied on a change…

Machine Learning · Statistics 2020-05-21 Florent Bouchard , Ammar Mian , Jialun Zhou , Salem Said , Guillaume Ginolhac , Yannick Berthoumieu

Imaging systems are represented as linear operators, and their singular value spectra describe the structure recoverable at the operator level. Building on an operator-based information-theoretic framework, this paper introduces a minimal…

Information Theory · Computer Science 2026-01-06 Charles Wood

Many statistical models require an estimation of unknown (co)-variance parameter(s) in a model. The estimation usually obtained by maximizing a log-likelihood which involves log determinant terms. In principle, one requires the…

Computation · Statistics 2016-09-05 Shengxin Zhu , Tongxiang Gu , Xiaowen Xu , Zeyao Mo

We present the cosmological distance errors achievable using the baryon acoustic oscillations as a standard ruler. We begin from a Fisher matrix formalism that is upgraded from Seo & Eisenstein (2003). We isolate the information from the…

Astrophysics · Physics 2011-02-11 Hee-Jong Seo , Daniel J. Eisenstein

We investigate the connection between the time-evolution of averages of stochastic quantities and the Fisher information and its induced statistical length. As a consequence of the Cramer-Rao bound, we find that the rate of change of the…

Statistical Mechanics · Physics 2020-07-01 Sosuke Ito , Andreas Dechant

Modern machine learning relies on a collection of empirically successful but theoretically heterogeneous regularization techniques, such as weight decay, dropout, and exponential moving averages. At the same time, the rapidly increasing…

Machine Learning · Computer Science 2026-01-27 Laurent Caraffa

In this paper, a distance between the Gaussian Mixture Models(GMMs) is obtained based on an embedding of the K-component Gaussian Mixture Model into the manifold of the symmetric positive definite matrices. Proof of embedding of K-component…

Differential Geometry · Mathematics 2025-01-14 Amit Vishwakarma , KS Subrahamanian Moosath

A deep neural network is a hierarchical nonlinear model transforming input signals to output signals. Its input-output relation is considered to be stochastic, being described for a given input by a parameterized conditional probability…

Machine Learning · Computer Science 2018-08-23 Shun-ichi Amari , Ryo Karakida , Masafumi Oizumi

In this article, we present recent developments of information geometry, namely, geometry of the Fisher metric, dualistic structures and divergences on the space of probability measures, particularly the theory of geodesics of the Fisher…

Differential Geometry · Mathematics 2022-08-29 Mitsuhiro Itoh , Hiroyasu Satoh

We consider the problems of clustering, classification, and visualization of high-dimensional data when no straightforward Euclidean representation exists. Typically, these tasks are performed by first reducing the high-dimensional data to…

Machine Learning · Statistics 2009-09-29 Kevin M. Carter , Raviv Raich , William G. Finn , Alfred O. Hero