High-probability generalization bounds for pointwise uniformly stable algorithms
From MaRDI portal
Cites work
- 10.1162/153244302760200704
- 10.1162/153244303321897690
- A finite sample distribution-free performance bound for local discrimination rules
- Capacity dependent analysis for functional online learning algorithms
- Concentration inequalities. A nonasymptotic theory of independence
- Differentially private SGD with non-smooth losses
- Distribution-free inequalities for the deleted and holdout error estimates
- High-dimensional probability. An introduction with applications in data science
- scientific article; zbMATH DE number 1301967 (Why is no real title available?)
- Learnability, stability and uniform convergence
- Learning Theory
- Online gradient descent algorithms for functional data learning
- Stability of randomized learning algorithms
- Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
- Support Vector Machines
- The covering number in learning theory
- Unregularized online learning algorithms with general loss functions
Cited in
(4)- On the convergence of gradient descent for robust functional linear regression
- Minibatch and local SGD: algorithmic stability and linear speedup in generalization
- Online outcome weighted learning with general loss functions
- A unified theoretical framework for the last-iterate convergence of stochastic adaptive optimization
This page was built for publication: High-probability generalization bounds for pointwise uniformly stable algorithms
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6122632)
