On spectral learning
From MaRDI portal
Recommendations
- Regularization techniques for learning with matrices
- Learning with tensors: a framework based on convex optimization and spectral regularization
- Spectral Algorithms for Supervised Learning
- Learning theory of distributed spectral algorithms
- Trace norm regularization: reformulations, algorithms, and multi-task learning
Cited in
(27)- Finite rank kernels for multi-task learning
- Regularizers for structured sparsity
- Rank penalized estimators for high-dimensional matrices
- Fixed-point proximity algorithm for minimal norm interpolation
- Learning rates for the kernel regularized regression with a differentiable strongly convex loss
- Learning with tensors: a framework based on convex optimization and spectral regularization
- Learning with optimal interpolation norms
- On reproducing kernel Banach spaces: generic definitions and unified framework of constructions
- Mathematical characterization of sophisticated variants for relevance learning in learning matrix quantization based on Schatten-p-norms
- Error bounds for learning the kernel
- Trace norm regularization: reformulations, algorithms, and multi-task learning
- Spectral Norm in Learning Theory: Some Selected Topics
- Learning Decision Trees Using the Fourier Spectrum
- scientific article; zbMATH DE number 2044185 (Why is no real title available?)
- Learning Power Spectrum Maps From Quantized Power Measurements
- A Comparative Study of Pairwise Learning Methods Based on Kernel Ridge Regression
- Margin error bounds for support vector machines on reproducing kernel Banach spaces
- Generalized Mercer kernels and reproducing kernel Banach spaces
- Regularization techniques for learning with matrices
- Estimation of high-dimensional low-rank matrices
- Minimum norm interpolation in the \(\ell_1(\mathbb{N})\) space
- White noise space analysis and multiplicative change of measures
- New Hilbert space tools for analysis of graph Laplacians and Markov processes
- Sparse and Low-Rank Matrix Quantile Estimation With Application to Quadratic Regression
- Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion
- Asymmetric and category invariant feature transformations for domain adaptation
- Harnessing lab knowledge for real-world action recognition
This page was built for publication: On spectral learning
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2896060)
