Online Learning as Stochastic Approximation of Regularization Paths: Optimality and Almost-Sure Convergence

DOI10.1109/TIT.2014.2332531MaRDI QIDQ2986183zbMATH OpenOpenAlexFDO

Authors Pierre Tarrès, Yuan Yao

Publication date 16 May 2017

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1109/tit.2014.2332531

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Stochastic approximation (62L20) Learning and adaptive systems in artificial intelligence (68T05)

Cited in

(35)

• Stochastic subspace correction in Hilbert space
• Generalization properties of doubly stochastic learning algorithms
• A loss bound model for on-line stochastic prediction algorithms
• Concentration bounds for temporal difference learning with linear function approximation: the case of batch data and uniform sampling
• A sieve stochastic gradient descent estimator for online nonparametric regression in Sobolev ellipsoids
• Fast and strong convergence of online learning algorithms
• Convergence analysis of online learning algorithm with two-stage step size
• Nonparametric stochastic approximation with large step-sizes
• Convergence of unregularized online learning algorithms
• Harder, Better, Faster, Stronger Convergence Rates for Least-Squares Regression
• scientific article; zbMATH DE number 6860836 (Why is no real title available?)
• On the regularizing property of stochastic gradient descent
• Learning theory of randomized sparse Kaczmarz method
• scientific article; zbMATH DE number 1569102 (Why is no real title available?)
• Online sufficient dimension reduction through sliced inverse regression
• Graph-dependent implicit regularisation for distributed stochastic subgradient descent
• Generalization performance of multi-pass stochastic gradient descent with convex loss functions
• An analysis of stochastic variance reduced gradient for linear inverse problems ^*
• Unregularized online learning algorithms with general loss functions
• Online Proximal Learning Over Jointly Sparse Multitask Networks With $\ell _{\infty, 1}$ Regularization
• On the Convergence of Stochastic Gradient Descent for Nonlinear Ill-Posed Problems
• scientific article; zbMATH DE number 7306853 (Why is no real title available?)
• Online local learning via semidefinite programming
• Online Pairwise Learning Algorithms
• Analysis of Online Composite Mirror Descent Algorithm
• An Online Projection Estimator for Nonparametric Regression in Reproducing Kernel Hilbert Spaces
• Online regularized learning algorithm for functional data
• Sparse online regression algorithm with insensitive loss functions
• Scalable inference in functional linear regression with streaming data
• Online estimation with rolling validation: adaptive nonparametric estimation with streaming data
• Online learning algorithms tackling covariate shift
• Sequential quantile regression for stream data by least squares
• Online outcome weighted learning with general loss functions
• Convergence analysis of online algorithms for vector-valued kernel regression
• Truncated kernel stochastic gradient descent on spheres

This page was built for publication: Online Learning as Stochastic Approximation of Regularization Paths: Optimality and Almost-Sure Convergence

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2986183)