A theoretical analysis of the test error of finite-rank kernel ridge regression

TS Cheng, A Lucchi, A Kratsios… - Advances in Neural …, 2023 - proceedings.neurips.cc
Existing statistical learning guarantees for general kernel regressors often yield loose
bounds when used with finite-rank kernels. Yet, finite-rank kernels naturally appear in a …

Random feature neural networks learn Black-Scholes type PDEs without curse of dimensionality

L Gonon - Journal of Machine Learning Research, 2023 - jmlr.org
This article investigates the use of random feature neural networks for learning Kolmogorov
partial (integro-) differential equations associated to Black-Scholes and more general …

Global universal approximation of functional input maps on weighted spaces

C Cuchiero, P Schmocker, J Teichmann - ar** mathematics of deep learning, we build universal functions
approximators of continuous maps between arbitrary Polish metric spaces $\mathcal {X} …

Essays in time series econometrics and machine learning

G Ballarin - 2024 - madoc.bib.uni-mannheim.de
This dissertation collects three works developed on the broad topic of time series analysis,
with a specific focus on machine learning, non-and semi-parametric methods, and …

[PDF][PDF] Universal Geometric Deep Learning via Geometric Attention

Geometric deep learning (GDL) is a rapidly growing area of machine learning which
leverages non-Euclidean structures, such as functions, graphs, or points on manifolds, into …