arXiv subjects

Sivananthan Sampath

Publications and source records attributed to Sivananthan Sampath.

6 recordsLinked to original sources

arXiv2025

Convergence Analysis of function-on-function Polynomial regression model

In this article, we study the convergence behavior of the regularization-based algorithm for solving the polynomial regression model when both input data and responses are from infinite-dimensional Hilbert spaces. We derive convergence rates for estimation and prediction error by employing general (spectral) regularization under a general smoothness condition without imposing any additional conditions on the index function. We also establish lower bounds for any learning algorithm to explain the optimality of our convergence rates.

math.ST↗

arXiv2024

Convergence Analysis of regularised Nyström method for Functional Linear Regression

The functional linear regression model has been widely studied and utilized for dealing with functional predictors. In this paper, we study the Nyström subsampling method, a strategy used to tackle the computational complexities inherent in big data analytics, especially within the domain of functional linear regression model in the framework of reproducing kernel Hilbert space. By adopting a Nyström subsampling strategy, our aim is to mitigate the computational overhead associated with kernel methods, which often struggle to scale gracefully with dataset size. Specifically, we investigate a regularization-based approach combined with Nyström subsampling for functional linear regression model, effectively reducing the computational complexity from $O(n^3)$ to $O(m^2 n)$, where $n$ represents the size of the observed empirical dataset and $m$ is the size of subsampled dataset. Notably, we establish that these methodologies will achieve optimal convergence rates, provided that the subsampling level is appropriately selected. We have also demonstrated a numerical example of Nyström subsampling in the RKHS framework for the functional linear regression model.

math.ST↗

arXiv2021

Random Sampling in Reproducing Kernel Subspace of Mixed Lebesgue Spaces

In this article, we consider the random sampling in the image space $V$ of mixed Lebesgue space $L^{p,q}(\mathbb{R}^{n+1})$ under an idempotent integral operator. We assume some decay and regularity conditions of the kernel and approximate the unit sphere in $V$ on a bounded cube $C_{R,S}$ by a finite-dimensional subspace of $V$. Consequently, the set of concentrated functions is totally bounded. We prove with an overwhelming probability that the random sample set uniformly distributed over $C_{R,S}$ is a stable set of sampling for the set of concentrated functions on $C_{R,S}$. Moreover, we propose an iterative scheme to reconstruct the concentrated signal from its random measurements.

math.FA↗

arXiv2019

Random Sampling in reproducing kernel subspaces of $L^p({\mathbb R}^n)$

In this paper, we study random sampling on reproducing kernel space $V$, which is a range of an idempotent integral operator. Under certain decay condition on the integral kernel, we show that any element in $V$ can be approximated by an element in a finite-dimensional subspace of $V$. Moreover, we prove with overwhelming probability that random points uniformly distributed over a cube $C$ is stable sample for the set of functions concentrated on $C$

math.FA↗

arXiv2017

Manifold regularization based on Nystr{ö}m type subsampling

In this paper, we study the Nystr{ö}m type subsampling for large scale kernel methods to reduce the computational complexities of big data. We discuss the multi-penalty regularization scheme based on Nystr{ö}m type subsampling which is motivated from well-studied manifold regularization schemes. We develop a theoretical analysis of multi-penalty least-square regularization scheme under the general source condition in vector-valued function setting, therefore the results can also be applied to multi-task learning problems. We achieve the optimal minimax convergence rates of multi-penalty regularization using the concept of effective dimension for the appropriate subsampling size. We discuss an aggregation approach based on linear function strategy to combine various Nystr{ö}m approximants. Finally, we demonstrate the performance of multi-penalty regularization based on Nystr{ö}m type subsampling on Caltech-101 data set for multi-class image classification and NSL-KDD benchmark data set for intrusion detection problem.

stat.ML↗

arXiv2017

Optimal rates for the regularized learning algorithms under general source condition

We consider the learning algorithms under general source condition with the polynomial decay of the eigenvalues of the integral operator in vector-valued function setting. We discuss the upper convergence rates of Tikhonov regularizer under general source condition corresponding to increasing monotone index function. The convergence issues are studied for general regularization schemes by using the concept of operator monotone index functions in minimax setting. Further we also address the minimum possible error for any learning algorithm.

stat.ML↗