Coefficient-based regularized distribution regression
From MaRDI portal
Abstract: In this paper, we consider the coefficient-based regularized distribution regression which aims to regress from probability measures to real-valued responses over a reproducing kernel Hilbert space (RKHS), where the regularization is put on the coefficients and kernels are assumed to be indefinite. The algorithm involves two stages of sampling, the first stage sample consists of distributions and the second stage sample is obtained from these distributions. Asymptotic behaviors of the algorithm in different regularity ranges of the regression function are comprehensively studied and learning rates are derived via integral operator techniques. We get the optimal rates under some mild conditions, which matches the one-stage sampled minimax optimal rate. Compared with the kernel methods for distribution regression in the literature, the algorithm under consideration does not require the kernel to be symmetric and positive semi-definite and hence provides a simple paradigm for designing indefinite kernel methods, which enriches the theme of the distribution regression. To the best of our knowledge, this is the first result for distribution regression with indefinite kernels, and our algorithm can improve the saturation effect.
Recommendations
- Optimal rates for coefficient-based regularized regression
- Distributed learning with indefinite kernels
- Distributed learning and distribution regression of coefficient regularization
- Coefficient-based regularized regression with indefinite kernels by unbounded sampling
- Coefficient-based \(l^q\)-regularized regression with indefinite kernels and unbounded sampling
Cites work
- 10.1162/jmlr.2003.3.4-5.651
- A Hilbert Space Embedding for Distributions
- A kernel two-sample test
- An RKHS approach to estimate individualized treatment rules based on functional predictors
- Causal Discovery via Reproducing Kernel Hilbert Space Embeddings
- Compressive learning with privacy guarantees
- Concentration estimates for learning with \(\ell ^{1}\)-regularizer and data dependent hypothesis spaces
- Concentration estimates for learning with unbounded sampling
- Distributed learning and distribution regression of coefficient regularization
- Distributed learning with indefinite kernels
- ESTIMATING THE APPROXIMATION ERROR IN LEARNING THEORY
- scientific article; zbMATH DE number 5957287 (Why is no real title available?)
- Indefinite proximity learning: a review
- Kernel Mean Embedding of Distributions: A Review and Beyond
- Learning Theory
- Learning theory estimates for coefficient-based regularized regression
- Learning theory estimates via integral operators and their approximations
- Learning theory of distributed spectral algorithms
- Least square regression with indefinite kernels and coefficient regularization
- Modeling interactive components by coordinate kernel polynomial models
- Nyström subsampling method for coefficient-based regularized regression
- On regularization algorithms in learning theory
- Optimal learning rates for distribution regression
- Optimal rates for coefficient-based regularized regression
- Optimal rates for the regularized least-squares algorithm
- Regularization networks with indefinite kernels
- Remarks on Inequalities for Large Deviation Probabilities
- Solving the multiple instance problem with axis-parallel rectangles.
- Support Vector Machines
Cited in
(2)
This page was built for publication: Coefficient-based regularized distribution regression
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6187678)
