Local Rademacher complexity-based learning guarantees for multi-task learning
From MaRDI portal
Recommendations
Cites work
- scientific article; zbMATH DE number 5957307 (Why is no real title available?)
- scientific article; zbMATH DE number 1113195 (Why is no real title available?)
- scientific article; zbMATH DE number 1552503 (Why is no real title available?)
- scientific article; zbMATH DE number 3442634 (Why is no real title available?)
- scientific article; zbMATH DE number 1448976 (Why is no real title available?)
- 10.1162/153244303321897690
- 10.1162/1532443041424337
- A Bennett concentration inequality and its application to suprema of empirical processes
- A Uniform Lower Error Bound for Half-Space Learning
- A chain rule for the expected suprema of Gaussian processes
- A new approach to least-squares estimation, with applications
- A notion of task relatedness yielding provable multiple-task learning guarantees
- Bounds for linear multi-task learning
- Concentration inequalities using the entropy method
- Concentration inequalities. A nonasymptotic theory of independence
- Convex multi-task feature learning
- Domain adaptation and sample bias correction theory and algorithm for regression
- Domain adaptation in regression
- Empirical margin distributions and bounding the generalization error of combined classifiers
- Generalization Bounds for K-Dimensional Coding Schemes in Hilbert Spaces
- Learning Theory
- Learning Theory
- Learning Theory
- Learning Theory and Kernel Machines
- Learning multiple tasks with kernel methods
- Learning without concentration
- Local Rademacher complexities
- Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
- Local Rademacher complexity: sharper risk bounds with and without unlabeled samples
- Model selection and error estimation
- Multi-task and lifelong learning of kernels
- Multi-task learning for computational biology: overview and outlook
- On the convergence rate of \(l_{p}\)-norm multiple kernel learning
- Rademacher complexities and bounding the excess risk in active learning
- Rademacher penalties and structural risk minimization
- Regularization techniques for learning with matrices
- Robust domain adaptation
- Stability bounds for stationary -mixing and -mixing processes
- The Khintchine inequalities and martingale expanding sphere of their action
- The Rademacher Complexity of Linear Transformation Classes
- The benefit of multitask representation learning
- Trace norm regularization: reformulations, algorithms, and multi-task learning
- Weak convergence and empirical processes. With applications to statistics
Cited in
(6)- On the convergence rate of \(l_{p}\)-norm multiple kernel learning
- Multi-kernel learning for multi-label classification with local Rademacher complexity
- Towards empirical process theory for vector-valued functions: metric entropy of smooth function classes
- A characterization of multioutput learnability
- Factorisable multitask quantile regression
- Bounds for linear multi-task learning
This page was built for publication: Local Rademacher complexity-based learning guarantees for multi-task learning
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4558184)
