Large margin unified machines with non-i.i.d. process

DOI10.11948/20220222MaRDI QIDQ6599669FDOQ6599669

Authors: Amina Benabid, Dan Su, Dao-Hong Xiang 

Publication date: 6 September 2024

Published in: Journal of Applied Analysis and Computation (Search for Journal in Brave)

Recommendations

• Comparison theorems on large-margin learning
• Quantitative convergence analysis of kernel based large-margin unified machines
• Classification with non-i.i.d. sampling
• Regression learning with non-identically and non-independently sampling
• Error analysis of classification learning algorithms based on LUMs loss

zbMATH Keywords

reproducing kernel Hilbert spacesprojection operator\( \beta \)-mixing sequencelarge margin unified machines

Mathematics Subject Classification ID

Computational learning theory (68Q32) Approximation by arbitrary nonlinear expressions; widths and entropy (41A46)

Cites Work

• The elements of statistical learning. Data mining, inference, and prediction
• Distance-Weighted Discrimination
• Support-vector networks
• Lasso guarantees for \(\beta \)-mixing heavy-tailed time series
• Learning Theory
• Support vector machine soft margin classifiers: error analysis
• Title not available (Why is that?)
• The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network
• Hard or soft classification? Large-margin unified machines
• The covering number in learning theory
• Conditional quantiles with varying Gaussians
• Learning rates of least-square regularized regression
• Capacity of reproducing kernel spaces in learning theory
• Estimating conditional quantiles with the help of the pinball loss
• Multi-kernel regularized classifiers
• Fast rates for support vector machines using Gaussian kernels
• Rates of convergence for empirical processes of stationary mixing sequences
• Generalization performance of regularization networks and support vector machines via entropy numbers of compact operators
• Classification with Gaussians and convex loss
• ONLINE LEARNING WITH MARKOV SAMPLING
• Classification with non-i.i.d. sampling
• Regularized least square regression with dependent samples
• Learning rates of regularized regression for exponentially strongly mixing sequence
• Logistic classification with varying gaussians
• A Statistical Learning Approach to Modal Regression
• Modeling interactive components by coordinate kernel polynomial models
• Quantitative convergence analysis of kernel based large-margin unified machines
• Distributed minimum error entropy algorithms
• Comparison theorems on large-margin learning

This page was built for publication: Large margin unified machines with non-i.i.d. process

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6599669)