Learning from Non-iid Data: Fast Rates for the One-vs-All Multiclass Plug-in Classifiers

DOI10.1007/978-3-319-17142-5_32zbMath1459.68169arXiv1408.2714OpenAlexW311675162MaRDI QIDQ2948481

No author found.

Publication date: 30 September 2015

Published in: Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1408.2714

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (5)

Posterior concentration and fast convergence rates for generalized Bayesian learning ⋮ Adaptive group Lasso neural network models for functions of few variables and time-dependent data ⋮ An adaptive multiclass nearest neighbor classifier ⋮ Recovery guarantees for polynomial coefficients from weakly dependent data with outliers ⋮ Towards convergence rate analysis of random forests for classification

Cites Work

• Unnamed Item
• Unnamed Item
• Analysis of comparative data with hierarchical autocorrelation
• Fast rates for support vector machines using Gaussian kernels
• Fast learning rates for plug-in classifiers
• Exponential inequalities for sums of random vectors
• On the complexity of learning from drifting distributions
• Optimal aggregation of classifiers in statistical learning.
• Classification via local multi-resolution projections
• The complexity of learning according to two models of a drifting environment
• Generalization error for multi-class margin classification
• Fast learning from \(\alpha\)-mixing observations
• Generalization and Robustness of Batched Weighted Average Algorithm with V-Geometrically Ergodic Markov Data
• New Analysis and Algorithm for Learning with Drifting Distributions
• On the Rate of Convergence of Local Averaging Plug-In Classification Rules Under a Margin Condition
• Minimum complexity regression estimation with weakly dependent observations
• Plug-in Approach to Active Learning
• Prediction of time series by statistical learning: general losses and fast rates

This page was built for publication: Learning from Non-iid Data: Fast Rates for the One-vs-All Multiclass Plug-in Classifiers