English
Related papers

Related papers: Asymptotic Behavior of Integral Projection Models …

200 papers

The success of deep convolutional architectures is often attributed in part to their ability to learn multiscale and invariant representations of natural signals. However, a precise study of these properties and how they affect learning…

Machine Learning · Statistics 2019-02-14 Alberto Bietti , Julien Mairal

Determinantal point processes (DPPs) are point process models that naturally encode diversity between the points of a given realization, through a positive definite kernel $K$. DPPs possess desirable properties, such as exact sampling or…

Computation · Statistics 2015-07-07 Rémi Bardenet , Michalis K. Titsias

This paper studies Kernel Density Estimation for a high-dimensional distribution $\rho(x)$. Traditional approaches have focused on the limit of large number of data points $n$ and fixed dimension $d$. We analyze instead the regime where…

Machine Learning · Computer Science 2024-10-21 Giulio Biroli , Marc Mézard

Quantum machine learning (QML) represents a promising frontier in the quantum technologies. In this pursuit of quantum advantage, the quantum kernel method for support vector machine has emerged as a powerful approach. Entanglement, a…

Quantum Physics · Physics 2023-11-21 Haiyan Wang

Analyzing the structure of sampled features from an input data distribution is challenging when constrained by limited measurements in both the number of inputs and features. Traditional approaches often rely on the eigenvalue spectrum of…

Machine Learning · Computer Science 2025-02-11 Chanwoo Chun , SueYeon Chung , Daniel D. Lee

We consider a stochastic individual-based model in continuous time to describe a size-structured population for cell divisions. This model is motivated by the detection of cellular aging in biology. We address here the problem of…

Statistics Theory · Mathematics 2020-09-28 Van Ha Hoang , Thanh Mai Pham Ngoc , Vincent Rivoirard , Viet Chi Tran

Kernel methods approximate nonlinear maps in a data-driven manner by projecting the target map onto a finite-dimensional Hilbert space called the solution space. Traditionally, this space is a subspace of a fixed ambient reproducing kernel…

Numerical Analysis · Mathematics 2026-01-30 Tamás Dózsa , Andrea Angino , Zoltán Szabó , József Bokor , Matthias Voigt

From genomes and ecosystems to bureaucracies and cities, the growth of complex systems occurs by adding new types of functions and expanding existing ones. We present a simple generative model that generalizes the Yule-Simon process by…

Gaussian processes offers a convenient way to perform nonparametric reconstructions of observational data assuming only a kernel which describes the covariance between neighbouring points in a data set. We approach the ambiguity in the…

Cosmology and Nongalactic Astrophysics · Physics 2021-08-17 Reginald Christian Bernardo , Jackson Levi Said

Learning the kernel functions used in kernel methods has been a vastly explored area in machine learning. It is now widely accepted that to obtain 'good' performance, learning a kernel function is the key challenge. In this work we focus on…

Machine Learning · Computer Science 2016-01-08 Chetan Tonde , Ahmed Elgammal

This paper studies model selection for general unit-root time series, including the case with many exogenous predictors. We propose a new model selection algorithm, FHTD, that leverages forward stepwise regression (FSR), a high-dimensional…

Methodology · Statistics 2026-04-28 Shuo-Chieh Huang , Ching-Kang Ing , Ruey S. Tsay

Traditionally, kernel methods rely on the representer theorem which states that the solution to a learning problem is obtained as a linear combination of the data mapped into the reproducing kernel Hilbert space (RKHS). While elegant from…

Machine Learning · Computer Science 2021-08-30 Riikka Huusari , Sahely Bhadra , Cécile Capponi , Hachem Kadri , Juho Rousu

Integrative analysis of multiple heterogeneous datasets has become standard practice in many research fields, especially in single-cell genomics and medical informatics. Existing approaches oftentimes suffer from limited power in capturing…

Machine Learning · Statistics 2026-03-02 Xiucai Ding , Rong Ma

String equations related to 2D gravity seem to provide, quite naturally and systematically, integrable kernels, in the sense of Its-Izergin-Korepin and Slavnov. Some of these kernels (besides the "classical" examples of Airy and Pearcey)…

Mathematical Physics · Physics 2013-10-01 M. Adler , M. Cafasso , P. van Moerbeke

Geometric and Topological Deep Learning are rapidly growing research areas that enhance machine learning through the use of geometric and topological structures. Within this framework, Group Equivariant Non-Expansive Operators (GENEOs) have…

Representation Theory · Mathematics 2026-01-14 Francesco Conti , Patrizio Frosini , Nicola Quercioli

Understanding the relationship between cognition and intrinsic brain activity through purely data-driven approaches remains a significant challenge in neuroscience. Resting-state functional magnetic resonance imaging (rs-fMRI) offers a…

Machine Learning · Computer Science 2024-11-01 Yutong Gao , Vince D. Calhoun , Robyn L. Miller

Existing approaches for analyzing neural network activations, such as PCA and sparse autoencoders, rely on strong structural assumptions. Generative models offer an alternative: they can uncover structure without such assumptions and act as…

Machine Learning · Computer Science 2026-02-09 Grace Luo , Jiahai Feng , Trevor Darrell , Alec Radford , Jacob Steinhardt

We introduce a class of one-dimensional discrete space-discrete time stochastic growth models described by a height function $h_t(x)$ with corner initialization. We prove, with one exception, that the limiting distribution function of…

Probability · Mathematics 2009-09-25 Janko Gravner , Craig A. Tracy , Harold Widom

Evolutionary models for populations of constant size are frequently studied using the Moran model, the Wright-Fisher model, or their diffusion limits. When evolution is neutral, a random genealogy given through Kingman's coalescent is used…

Populations and Evolution · Quantitative Biology 2012-07-31 Peter Pfaffelhuber , Benedikt Vogt

The problem of estimating a parametric or nonparametric regression function in a model with normal errors is considered. For this purpose, a novel objective prior for the regression function is proposed, defined as the distribution…

Statistics Theory · Mathematics 2019-12-13 Wicher Bergsma
‹ Prev 1 8 9 10 Next ›