中文
相关论文

相关论文: Harmonic Map Regression: Rate-Optimal Nonparametri…

200 篇论文

We consider the fundamental task of optimising a real-valued function defined in a potentially high-dimensional Euclidean space, such as the loss function in many machine-learning tasks or the logarithm of the probability distribution in…

机器学习 · 统计学 2024-03-20 Marcelo Hartmann , Bernardo Williams , Hanlin Yu , Mark Girolami , Alessandro Barp , Arto Klami

Undirected graphical models are powerful tools for uncovering complex relationships among high-dimensional variables. This paper aims to fully recover the structure of an undirected graphical model when the data naturally take matrix form,…

统计方法学 · 统计学 2025-08-08 Minsub Shin , Johan Lim , Seongoh Park

Families of conformal field theories are naturally endowed with a Riemannian geometry which is locally encoded by correlation functions of exactly marginal operators. We show that the curvature of such conformal manifolds can be computed…

高能物理 - 理论 · 物理学 2023-08-09 Bruno Balthazar , Clay Cordova

We consider the regression problem of estimating functions on $\mathbb{R}^D$ but supported on a $d$-dimensional manifold $ \mathcal{M} \subset \mathbb{R}^D $ with $ d \ll D $. Drawing ideas from multi-resolution analysis and nonlinear…

机器学习 · 统计学 2021-01-14 Wenjing Liao , Mauro Maggioni , Stefano Vigogna

Let $S$ be a punctured Riemann surface with Euler characteristic $\chi(S)<0$. For any unitary representation $\rho: \pi_1(S) \to U(N)$, we introduce its renormalized energy and its harmonic representatives, which are equivariant harmonic…

微分几何 · 数学 2025-08-29 Antoine Song

Local Fr\'echet regression is a nonparametric regression method for metric space valued responses and Euclidean predictors, which can be utilized to obtain estimates of smooth trajectories taking values in general metric spaces from noisy…

统计方法学 · 统计学 2021-07-07 Yaqing Chen , Hans-Georg Müller

Model selection and sparse recovery are two important problems for which many regularization methods have been proposed. We study the properties of regularization methods in both problems under the unified framework of regularized least…

统计理论 · 数学 2009-09-03 Jinchi Lv , Yingying Fan

The matching problem is a notorious combinatorial optimization problem that has attracted for many years the attention of the statistical physics community. Here we analyze the Euclidean version of the problem, i.e. the optimal matching…

无序系统与神经网络 · 物理学 2017-01-11 Carlo Lucibello , Giorgio Parisi , Gabriele Sicuro

Non-Euclidean data that are indexed with a scalar predictor such as time are increasingly encountered in data applications, while statistical methodology and theory for such random objects are not well developed yet. To address the need for…

统计方法学 · 统计学 2021-08-24 Zhenhua Lin , Hans-Georg Müller

We study the Dirichlet problem for harmonic maps between hyperbolic planes, under the assumption that the Euclidean harmonic extension of the boundary map is quasiconformal.

偏微分方程分析 · 数学 2014-06-18 Anestis Fotiadis

We study the existence of harmonic maps and Dirac-harmonic maps from degenerating surfaces to non-positive curved manifold via the scheme of Sacks and Uhlenbeck. By choosing a suitable sequence of $\alpha$-(Dirac-)harmonic maps from a…

微分几何 · 数学 2021-06-25 Jürgen Jost , Jingyong Zhu

We present a novel approach for the inverse problem in electrical impedance tomography based on regularized quadratic regression. Our contribution introduces a new formulation for the forward model in the form of a nonlinear integral…

地球物理 · 物理学 2012-05-29 Nick Polydorides , Alireza Aghasi , Eric L. Miller

Statistical analysis is increasingly confronted with complex data from metric spaces. Petersen and M\"uller (2019) established a general paradigm of Fr\'echet regression with complex metric space valued responses and Euclidean predictors.…

机器学习 · 统计学 2025-02-10 Rui Qiu , Zhou Yu , Ruoqing Zhu

We investigate the problem of recovering a partially observed high-rank matrix whose columns obey a nonlinear structure such as a union of subspaces, an algebraic variety or grouped in clusters. The recovery problem is formulated as the…

机器学习 · 统计学 2022-12-12 Florentin Goyens , Coralia Cartis , Armin Eftekhari

High-dimensional data subject to heavy-tailed phenomena and heterogeneity are commonly encountered in various scientific fields and bring new challenges to the classical statistical methods. In this paper, we combine the asymmetric square…

统计理论 · 数学 2019-10-02 Jun Zhao , Guan'ao Yan , Yi Zhang

This article deals with error estimates for the finite element approximation of variational normal derivatives and, as a consequence, error estimates for the finite element approximation of Dirichlet boundary control problems with energy…

数值分析 · 数学 2018-08-06 Max Winkler

We prove a ${\Gamma}$-convergence result for the $p$-Dirichlet energy functional defined on maps from a smooth bounded domain $\Omega \subseteq \mathbb{R}^{n+k}$ to $\mathscr{N}$, a $(k-2)$-connected and smooth closed Riemannian manifold…

偏微分方程分析 · 数学 2025-05-28 Giacomo Canevari , Van Phu Cuong Le , Ramon Oliver-Bonafoux , Giandomenico Orlandi

This paper extends the recently developed framework of multilinear kernel regression and imputation via manifold learning (MultiL-KRIM) to impute time-varying edge flows in a graph. MultiL-KRIM uses simplicial-complex arguments and Hodge…

机器学习 · 计算机科学 2024-09-10 Duc Thien Nguyen , Konstantinos Slavakis , Dimitris Pados

Recent theoretical studies proved that deep neural network (DNN) estimators obtained by minimizing empirical risk with a certain sparsity constraint can attain optimal convergence rates for regression and classification problems. However,…

统计理论 · 数学 2021-08-10 Ilsang Ohn , Yongdai Kim

High-dimensional data analysis has been an active area, and the main focuses have been variable selection and dimension reduction. In practice, it occurs often that the variables are located on an unknown, lower-dimensional nonlinear…

统计理论 · 数学 2012-07-31 Ming-Yen Cheng , Hau-tieng Wu