Zobrazeno 1 - 10
of 43 256
pro vyhledávání: '"Rates of convergence"'
Autor:
Peng, Jingfu, Yang, Yuhong
Recent research shows the susceptibility of machine learning models to adversarial attacks, wherein minor but maliciously chosen perturbations of the input can significantly degrade model performance. In this paper, we theoretically analyse the limit
Externí odkaz:
http://arxiv.org/abs/2410.09402
Autor:
Bigot, Aurélie
We provide rates of convergence in the central limit theorem in terms of projective criteria for adapted stationary sequences of centered random variables taking values in Banach spaces, with finite moment of order $p \in ]2,3]$ as soon as the centra
Externí odkaz:
http://arxiv.org/abs/2409.15787
Autor:
Petersen, Alexander
Estimation of the mean and covariance parameters for functional data is a critical task, with local linear smoothing being a popular choice. In recent years, many scientific domains are producing multivariate functional data for which $p$, the number
Externí odkaz:
http://arxiv.org/abs/2408.01326
Autor:
Bhowal, Sanchayan, Mukherjee, Somabha
In this paper, we derive distributional convergence rates for the magnetization vector and the maximum pseudolikelihood estimator of the inverse temperature parameter in the tensor Curie-Weiss Potts model. Limit theorems for the magnetization vector
Externí odkaz:
http://arxiv.org/abs/2406.15907
Autor:
Chen, Hengchao
Manifold data analysis is challenging due to the lack of parametric distributions on manifolds. To address this, we introduce a series of Riemannian radial distributions on Riemannian symmetric spaces. By utilizing the symmetry, we show that for many
Externí odkaz:
http://arxiv.org/abs/2405.07852
Autor:
Stewart, Jonathan R.
Local dependence random graph models are a class of block models for network data which allow for dependence among edges under a local dependence assumption defined around the block structure of the network. Since being introduced by Schweinberger an
Externí odkaz:
http://arxiv.org/abs/2404.11464
Autor:
Durot, Cecile, Mukherjee, Debarghya
Shuffled regression and unlinked regression represent intriguing challenges that have garnered considerable attention in many fields, including but not limited to ecological regression, multi-target tracking problems, image denoising, etc. However, a
Externí odkaz:
http://arxiv.org/abs/2404.09306
L\'evy's Upward Theorem says that the conditional expectation of an integrable random variable converges with probability one to its true value with increasing information. In this paper, we use methods from effective probability theory to characteri
Externí odkaz:
http://arxiv.org/abs/2403.19978
We study approximation and learning capacities of convolutional neural networks (CNNs) with one-side zero-padding and multiple channels. Our first result proves a new approximation bound for CNNs with certain constraint on the weights. Our second res
Externí odkaz:
http://arxiv.org/abs/2403.16459
We study parabolic semigroups of finite shift in the unit disk with regard to the rate of convergence of their orbits to the Denjoy--Wolff point. We examine this rate in terms of Euclidean distance, hyperbolic distance and harmonic measure. In each c
Externí odkaz:
http://arxiv.org/abs/2403.06883