Learnability, stability and uniform convergence

zbMATH Open1242.68247MaRDI QIDQ2896159FDOQ2896159

Authors: Shai Shalev-Shwartz, Ohad Shamir, Nathan Srebro, Karthik Sridharan 

Publication date: 13 July 2012

Published in: Journal of Machine Learning Research (JMLR) (Search for Journal in Brave)

Full work available at URL: http://www.jmlr.org/papers/v11/shalev-shwartz10a.html

Recommendations

• On learnability, complexity and stability
• Learning theory: stability is sufficient for generalization and necessary and sufficient for consistency of empirical risk minimization
• STABILITY RESULTS IN LEARNING THEORY
• A survey on learning theory. I: Stability and generalization
• Scale-sensitive dimensions, uniform convergence, and learnability

zbMATH Keywords

uniform convergencestabilitystatistical learning theorylearnabilitystochastic convex optimization

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05) Computational learning theory (68Q32)

Cited In (46)

• Fluctuations, effective learnability and metastability in analysis
• Robust regression using biased objectives
• Efficient and reliable overlay networks for decentralized federated learning
• Test Data Reuse for the Evaluation of Continuously Evolving Classification Algorithms Using the Area under the Receiver Operating Characteristic Curve
• Graph-dependent implicit regularisation for distributed stochastic subgradient descent
• Realizable learning is all you need
• Kernel selection with spectral perturbation stability of kernel matrix
• Relative utility bounds for empirically optimal portfolios
• Understanding generalization error of SGD in nonconvex optimization
• For interpolating kernel machines, minimizing the norm of the ERM solution maximizes stability
• Learning theory: stability is sufficient for generalization and necessary and sufficient for consistency of empirical risk minimization
• On learnability, complexity and stability
• Title not available (Why is that?)
• Statistical computational learning
• Learnability with respect to fixed distributions
• Algorithmic stability for adaptive data analysis
• Title not available (Why is that?)
• Consistency of learning algorithms using Attouch-Wets convergence
• A selective overview of deep learning
• Optimal transport: fast probabilistic approximation with exact solvers
• Title not available (Why is that?)
• Stability and Convergence of Principal Component Learning Algorithms
• Quantitative stability of barycenters in the Wasserstein space
• Sample Size Estimates for Risk-Neutral Semilinear PDE-Constrained Optimization
• On the consistency of the empirical risk minimization principle based on algorithmic stability
• Complementary composite minimization, small gradients in general norms, and applications
• Sample complexity of sample average approximation for conditional stochastic optimization
• Parsimonious online learning with kernels via sparse projections in function space
• Stability behavior for unsupervised learning
• A Statistical Learning Theory Approach for the Analysis of the Trade-off Between Sample Size and Precision in Truncated Ordinary Least Squares
• Title not available (Why is that?)
• A theoretical framework for deep transfer learning
• Title not available (Why is that?)
• A moment-matching approach to testable learning and a new characterization of Rademacher complexity
• Stability is stable: connections between replicability, privacy, and adaptive generalization
• Diametrical risk minimization: theory and computations
• Compressive sensing and neural networks from a statistical learning perspective
• Sample average approximations of strongly convex stochastic programs in Hilbert spaces
• Closure properties of uniform convergence of empirical means and PAC learnability under a family of probability measures.
• Perturbation of convex risk minimization and its application in differential private learning algorithms
• Average stability is invariant to data preconditioning. Implications to exp-concave empirical risk minimization
• Stability
• Toward nonlinear local reinforcement learning rules through neuroevolution
• Title not available (Why is that?)
• Optimal algorithms for differentially private stochastic monotone variational inequalities and saddle-point problems
• High-probability generalization bounds for pointwise uniformly stable algorithms

This page was built for publication: Learnability, stability and uniform convergence

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2896159)