Coefficient-based \(l^q\)-regularized regression with indefinite kernels and unbounded sampling
From MaRDI portal
Publication:1784975
DOI10.1016/j.jat.2018.07.003zbMath1398.68437OpenAlexW2887553323MaRDI QIDQ1784975
Qin Guo, Cheng Wang, Pei Xin Ye
Publication date: 27 September 2018
Published in: Journal of Approximation Theory (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1016/j.jat.2018.07.003
indefinite kernellearning ratecoefficient-based regularized regressionmoment hypothesisstepping stone function
General nonlinear regression (62J02) Learning and adaptive systems in artificial intelligence (68T05)
Related Items (2)
Optimality of the rescaled pure greedy learning algorithms ⋮ Analysis of Regression Algorithms with Unbounded Sampling
Cites Work
- Unnamed Item
- Unnamed Item
- Sharp learning rates of coefficient-based \(l^q\)-regularized regression with indefinite kernels
- Constructive analysis for coefficient regularization regression algorithms
- Learning by nonsymmetric kernels with data dependent spaces and \(\ell^1\)-regularizer
- Concentration estimates for learning with \(\ell ^{1}\)-regularizer and data dependent hypothesis spaces
- Optimal learning rates for least squares regularized regression with unbounded sampling
- Least square regression with indefinite kernels and coefficient regularization
- Unified approach to coefficient-based regularized regression
- Learning rates for least square regressions with coefficient regularization
- Learning theory estimates for coefficient-based regularized regression
- Concentration estimates for learning with unbounded sampling
- Multiscale kernels
- Some results on Tchebycheffian spline functions and stochastic processes
- Learning theory estimates via integral operators and their approximations
- On the mathematical foundations of learning
- Coefficient-based regularized regression with dependent and unbounded sampling
- Coefficient regularized regression with non-iid sampling
- Learning Theory
This page was built for publication: Coefficient-based \(l^q\)-regularized regression with indefinite kernels and unbounded sampling
