Manifold regularization based on Nyström type subsampling
From MaRDI portal
Publication:2175018
DOI10.1016/J.ACHA.2018.12.002zbMATH Open1494.68209arXiv1710.04872OpenAlexW2766675239MaRDI QIDQ2175018FDOQ2175018
Authors: Abhishake, S. Sivananthan 
Publication date: 27 April 2020
Published in: Applied and Computational Harmonic Analysis (Search for Journal in Brave)
Abstract: In this paper, we study the Nystr{"o}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{"o}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{"o}m approximants. Finally, we demonstrate the performance of multi-penalty regularization based on Nystr{"o}m type subsampling on Caltech-101 data set for multi-class image classification and NSL-KDD benchmark data set for intrusion detection problem.
Full work available at URL: https://arxiv.org/abs/1710.04872
Recommendations
- Nyström type subsampling analyzed as a regularized projection
- Nyström subsampling method for coefficient-based regularized regression
- Regularized Nyström subsampling in regression and ranking problems under general smoothness assumptions
- Analysis of regularized Nyström subsampling for regression functions of low smoothness
- Nyström-based approximate kernel subspace learning
manifold learningmulti-task learningmulti-penalty regularizationoptimal rateslinear functional strategyNyström-type subsampling
Learning and adaptive systems in artificial intelligence (68T05) Computational aspects of data analysis and big data (68T09)
Cites Work
- Learning deep architectures for AI
- On Learning Vector-Valued Functions
- Theory of Reproducing Kernels
- On the mathematical foundations of learning
- Title not available (Why is that?)
- Optimal rates for the regularized least-squares algorithm
- Geometry of linear ill-posed problems in variable Hilbert scales
- Learning the kernel function via regularization
- Title not available (Why is that?)
- Convex multi-task feature learning
- Adaptive kernel methods using the balancing principle
- Multi-penalty regularization in learning theory
- Learning from examples as an inverse problem
- Manifold regularization: a geometric framework for learning from labeled and unlabeled examples
- Title not available (Why is that?)
- On regularization algorithms in learning theory
- Marketing models of consumer heterogeneity
- Learning multiple tasks with kernel methods
- Neural Network Learning as an Inverse Problem
- Discretization strategy for linear ill-posed problems in variable Hilbert scales
- Design of Non-Linear Kernel Dictionaries for Object Recognition
- Direct estimation of linear functionals from indirect noisy observations
- A linear functional strategy for regularized ranking
- Learning theory of distributed spectral algorithms
- A unifying framework in vector-valued reproducing kernel Hilbert spaces for manifold regularization and co-regularized multi-view learning
- Pathway-based kernel boosting for the analysis of genome-wide association studies
- Multiple Kernel Sparse Representations for Supervised and Unsupervised Learning
- Nyström type subsampling analyzed as a regularized projection
- Aggregation of regularized solutions from multiple observation models
- Multi-task learning via linear functional strategy
- Practical Bayesian support vector regression for financial time series prediction and market condition change detection
- Structured Kernel Dictionary Learning With Correlation Constraint for Object Recognition
- Group-Sensitive Multiple Kernel Learning for Object Recognition
Cited In (2)
Uses Software
This page was built for publication: Manifold regularization based on Nyström type subsampling
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2175018)
