The Generalization Ability of Online Algorithms for Dependent Data
From MaRDI portal
Publication:2989484
DOI10.1109/TIT.2012.2212414zbMath1364.68372arXiv1110.2529OpenAlexW2127684734MaRDI QIDQ2989484
Publication date: 8 June 2017
Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1110.2529
Related Items (13)
Sampling and empirical risk minimization ⋮ Generalization bounds for non-stationary mixing processes ⋮ Simpler PAC-Bayesian bounds for hostile data ⋮ Discrepancy-based theory and algorithms for forecasting non-stationary time series ⋮ Stochastic online convex optimization. Application to probabilistic time series forecasting ⋮ Statistical learning based on Markovian data maximal deviation inequalities and learning rates ⋮ On biased random walks, corrupted intervals, and learning under adversarial design ⋮ Empirical risk minimization and complexity of dynamical models ⋮ Generalization ability of online pairwise support vector machine ⋮ Prediction of time series by statistical learning: general losses and fast rates ⋮ Optimal learning with Bernstein Online Aggregation ⋮ Unnamed Item ⋮ SVM-boosting based on Markov resampling: theory and algorithm
This page was built for publication: The Generalization Ability of Online Algorithms for Dependent Data