Online gradient descent algorithms for functional data learning
Functional linear model is a fruitfully applied general framework for regression problems,
including those with intrinsically infinite-dimensional data. Online gradient descent methods …
including those with intrinsically infinite-dimensional data. Online gradient descent methods …
Physics-informed machine learning as a kernel method
Physics-informed machine learning combines the expressiveness of data-based
approaches with the interpretability of physical models. In this context, we consider a …
approaches with the interpretability of physical models. In this context, we consider a …
Sample complexity and effective dimension for regression on manifolds
We consider the theory of regression on a manifold using reproducing kernel Hilbert space
methods. Manifold models arise in a wide variety of modern machine learning problems …
methods. Manifold models arise in a wide variety of modern machine learning problems …
Tikhonov regularization with oversmoothing penalty for nonlinear statistical inverse problems
A Rastogi - arXiv preprint arXiv:2002.01303, 2020 - arxiv.org
In this paper, we consider the nonlinear ill-posed inverse problem with noisy data in the
statistical learning setting. The Tikhonov regularization scheme in Hilbert scales is …
statistical learning setting. The Tikhonov regularization scheme in Hilbert scales is …
Effect of dimensionality on convergence rates of kernel ridge regression estimator
KY Bak, W Lee - Journal of Statistical Planning and Inference, 2024 - Elsevier
Despite the curse of dimensionality, kernel ridge regression often exhibits good performance
in practical applications, even when the dimension is moderately large. However, it has …
in practical applications, even when the dimension is moderately large. However, it has …
Inverse learning in Hilbert scales
A Rastogi, P Mathé - Machine Learning, 2023 - Springer
We study linear ill-posed inverse problems with noisy data in the framework of statistical
learning. The corresponding linear operator equation is assumed to fit a given Hilbert scale …
learning. The corresponding linear operator equation is assumed to fit a given Hilbert scale …
Optimal Learning Rates for Regularized Least-Squares with a Fourier Capacity Condition
P Talwai, D Simchi-Levi - arXiv preprint arXiv:2204.07856, 2022 - arxiv.org
We derive minimax adaptive rates for a new, broad class of Tikhonov-regularized learning
problems in Hilbert scales under general source conditions. Our analysis does not require …
problems in Hilbert scales under general source conditions. Our analysis does not require …
[PDF][PDF] STRUCTURED STATISTICAL ESTIMATION VIA OPTIMIZATION
AD McRae - 2022 - admcrae.github.io
In this chapter, 1 we consider the problem of estimating a low-rank matrix from the
observation of all or a subset of its entries in the presence of Poisson noise. When we …
observation of all or a subset of its entries in the presence of Poisson noise. When we …