English
Related papers

Related papers: Differential geometry with extreme eigenvalues in …

200 papers

We propose a differentially private data generation paradigm using random feature representations of kernel mean embeddings when comparing the distribution of true data with that of synthetic data. We exploit the random feature…

Machine Learning · Computer Science 2021-06-02 Frederik Harder , Kamil Adamczewski , Mijung Park

Curvature properties of convex objects, such as strong convexity, are important in designing and analyzing convex optimization algorithms in the Hilbertian or Riemannian settings. In the case of the Hilbertian setting, strongly convex sets…

Optimization and Control · Mathematics 2024-12-17 Damien Scieur , David Martínez-Rubio , Thomas Kerdreux , Alexandre d'Aspremont , Sebastian Pokutta

We propose a new method for spatial power spectrum estimation in array processing that leverages the Riemannian geometry of Hermitian positive definite (HPD) matrices. We show that conventional approaches minimize variants of the Euclidean…

Signal Processing · Electrical Eng. & Systems 2026-05-13 Or Cohen , Alon Amar , Ronen Talmon

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…

Differential Geometry · Mathematics 2020-01-07 Florent Bouchard , Arnaud Breloy , Guillaume Ginolhac , Alexandre Renaux , Frédéric Pascal

In this paper a geometric characterization of the unique geodesics in Thompson's metric spaces is presented. This characterization is used to prove a variety of other geometric results. Firstly, it will be shown that there exists a unique…

Metric Geometry · Mathematics 2013-05-30 Bas Lemmens , Mark Roelands

We reconsider randomized algorithms for the low-rank approximation of symmetric positive semi-definite (SPSD) matrices such as Laplacian and kernel matrices that arise in data analysis and machine learning applications. Our main results…

Machine Learning · Computer Science 2013-06-05 Alex Gittens , Michael W. Mahoney

Recently, a lot of attention has been devoted to finding physically realisable operations that realise as closely as possible certain desired transformations between quantum states, e.g. quantum cloning, teleportation, quantum gates, etc.…

Quantum Physics · Physics 2013-04-25 K. Audenaert , B. De Moor

An increasingly common viewpoint is that protein dynamics data sets reside in a non-linear subspace of low conformational energy. Ideal data analysis tools for such data sets should therefore account for such non-linear geometry. The…

Biomolecules · Quantitative Biology 2023-10-27 Willem Diepeveen , Carlos Esteve-Yagüe , Jan Lellmann , Ozan Öktem , Carola-Bibiane Schönlieb

Shape constraints, such as non-negativity, monotonicity, convexity or supermodularity, play a key role in various applications of machine learning and statistics. However, incorporating this side information into predictive models in a hard…

Machine Learning · Statistics 2022-11-22 Pierre-Cyril Aubin-Frankowski , Zoltan Szabo

In this paper, we comparatively analyze the Bures-Wasserstein (BW) geometry with the popular Affine-Invariant (AI) geometry for Riemannian optimization on the symmetric positive definite (SPD) matrix manifold. Our study begins with an…

Optimization and Control · Mathematics 2021-06-02 Andi Han , Bamdev Mishra , Pratik Jawanpuria , Junbin Gao

It is a standard assumption that datasets in high dimension have an internal structure which means that they in fact lie on, or near, subsets of a lower dimension. In many instances it is important to understand the real dimension of the…

Machine Learning · Statistics 2025-07-21 James A. D. Binnie , Paweł Dłotko , John Harvey , Jakub Malinowski , Ka Man Yim

Bayesian inference problems require sampling or approximating high-dimensional probability distributions. The focus of this paper is on the recently introduced Stein variational gradient descent methodology, a class of algorithms that rely…

Machine Learning · Statistics 2023-02-14 A. Duncan , N. Nuesken , L. Szpruch

Covariance matrices have proven highly effective across many scientific fields. Since these matrices lie within the Symmetric Positive Definite (SPD) manifold - a Riemannian space with intrinsic non-Euclidean geometry, the primary challenge…

Machine Learning · Computer Science 2025-04-02 Rui Wang , Shaocheng Jin , Ziheng Chen , Xiaoqing Luo , Xiao-Jun Wu

In this paper, a class of holomorphic invariant metrics is introduced on the irreducible classical domains of type I-IV, which are strongly pseudoconvex complex Finsler metrics in the strict sense of M. Abate and G. Patrizio[2]. These…

Differential Geometry · Mathematics 2023-04-11 Xiaoshu Ge , Chunping Zhong

Computing spectra is a central problem in computational mathematics with an abundance of applications throughout the sciences. However, in many applications gaining an approximation of the spectrum is not enough. Often it is vital to…

Spectral Theory · Mathematics 2022-09-20 Matthew J. Colbrook

Symmetric Positive Definite (SPD) matrices have been widely used in medical data analysis and a number of different Riemannian met-rics were proposed to compute with them. However, there are very few methodological principles guiding the…

Differential Geometry · Mathematics 2019-06-05 Yann Thanwerdas , Xavier Pennec

Optimization with constraints is a typical problem in quantum physics and quantum information science that becomes especially challenging for high-dimensional systems and complex architectures like tensor networks. Here we use ideas of…

Quantum Physics · Physics 2021-11-18 Ilia A. Luchnikov , Mikhail E. Krechetov , Sergey N. Filippov

Deep generative models learn a mapping from a low dimensional latent space to a high-dimensional data space. Under certain regularity conditions, these models parameterize nonlinear manifolds in the data space. In this paper, we investigate…

Machine Learning · Computer Science 2017-11-23 Hang Shao , Abhishek Kumar , P. Thomas Fletcher

In statistical applications it has become increasingly common to encounter data structures that live on non-linear spaces such as manifolds. Classical linear regression, one of the most fundamental methodologies of statistical learning,…

Machine Learning · Statistics 2026-02-10 Aditya Kulkarni , Carlos Soto

In this paper, we mainly focus on the set-valued (stochastic) analysis on the space of convex, closed, but possibly unbounded sets, and try to establish a useful theoretical framework for studying the set-valued stochastic differential…

Probability · Mathematics 2024-03-26 Atiqah Almuzaini , Jin Ma