Learning from examples as an inverse problem

zbMATH Open1222.68180MaRDI QIDQ3093282FDOQ3093282

Authors: Lorenzo Rosasco, Umberto de Giovannini, Francesca Odone, Ernesto De Vito, Andrea Caponnetto 

Publication date: 12 October 2011

Full work available at URL: http://www.jmlr.org/papers/v6/devito05a.html

Recommendations

• On regularization algorithms in learning theory
• AN ERROR ANALYSIS OF LAVRENTIEV REGULARIZATION IN LEARNING THEORY
• Regularization and statistical learning theory for data analysis.
• Tikhonov, Ivanov and Morozov regularization for support vector machine learning
• Neural Network Learning as an Inverse Problem

zbMATH Keywords

consistencystatistical learninginverse problemsregularization theory

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Linear operators and ill-posed problems, regularization (47A52)

Cited In (64)

• Learning particle swarming models from data with Gaussian processes
• Analysis of regularized least squares ranking with centered reproducing kernel
• Learning spectral windowing parameters for regularization using unbiased predictive risk and generalized cross validation techniques for multiple data sets
• Spectral algorithms for learning with dependent observations
• Least squares approximations in linear statistical inverse learning problems
• Convergence Rates for Learning Linear Operators from Noisy Data
• Regularized Nyström Subsampling in Covariate Shift Domain Adaptation Problems
• Convergence Rates of Spectral Regularization Methods: A Comparison between Ill-Posed Inverse Problems and Statistical Kernel Learning
• Kernel methods in system identification, machine learning and function estimation: a survey
• A multiscale support vector regression method on spheres with data compression
• A consistent and numerically efficient variable selection method for sparse Poisson regression with applications to learning and signal recovery
• Two-Layer Neural Networks with Values in a Banach Space
• Mini-workshop: Deep learning and inverse problems. Abstracts from the mini-workshop held March 4--10, 2018
• A note on the prediction error of principal component regression in high dimensions
• Title not available (Why is that?)
• Learning theory of distributed spectral algorithms
• Machine learning with kernels for portfolio valuation and risk management
• Kernel regression, minimax rates and effective dimensionality: beyond the regular case
• Tikhonov, Ivanov and Morozov regularization for support vector machine learning
• Generalized Kalman smoothing: modeling and algorithms
• Ensemble Kalman inversion: a derivative-free technique for machine learning tasks
• Kernel variable selection for multicategory support vector machines
• Thresholded spectral algorithms for sparse approximations
• Smoothed residual stopping for statistical inverse problems via truncated SVD estimation
• Wasserstein-based projections with applications to inverse problems
• Distributed least squares prediction for functional linear regression*
• Error analysis on regularized regression based on the maximum correntropy criterion
• Learning regularization parameters for general-form Tikhonov
• Multi-penalty regularization in learning theory
• Manifold regularization based on Nyström type subsampling
• Feasibility-based fixed point networks
• Convergence rates of kernel conjugate gradient for random design regression
• An elementary analysis of ridge regression with random design
• Kernel partial least squares for stationary data
• Complexity control in statistical learning
• On regularization algorithms in learning theory
• Diffusion maps for changing data
• Optimal rates for regularization of statistical inverse learning problems
• Neural Network Learning as an Inverse Problem
• Efficient regularized least-squares algorithms for conditional ranking on relational data
• Machine learning from examples: Inductive and Lazy methods
• Regularization: From Inverse Problems to Large-Scale Machine Learning
• Title not available (Why is that?)
• Nyström type subsampling analyzed as a regularized projection
• Optimal filters from calibration data for image deconvolution with data acquisition error
• On spectral windows in supervised learning from data
• A study on regularization for discrete inverse problems with model-dependent noise
• Regression learning based on incomplete relationships between attributes
• Multi-output learning via spectral filtering
• Adaptive kernel methods using the balancing principle
• Multi-task learning via linear functional strategy
• Title not available (Why is that?)
• Learning from non-random data in Hilbert spaces: an optimal recovery perspective
• Neural nets learning as an inverse problem
• Sobolev norm learning rates for regularized least-squares algorithms
• On a regularization of unsupervised domain adaptation in RKHS
• Random discretization of the finite Fourier transform and related kernel random matrices
• Statistical performance of support vector machines
• Estimating adsorption isotherm parameters in chromatography via a virtual injection promoting double feed-forward neural network
• Regularization and statistical learning theory for data analysis.
• Representation and reconstruction of covariance operators in linear inverse problems
• Convex regularization in statistical inverse learning problems
• Geometry on probability spaces
• Consistent learning by composite proximal thresholding

This page was built for publication: Learning from examples as an inverse problem

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3093282)