LEAST SQUARE REGRESSION WITH COEFFICIENT REGULARIZATION BY GRADIENT DESCENT

DOI10.1142/S021969131100447XzbMath1280.68168MaRDI QIDQ2893483

Luoqing Li, Hong Chen, Juan Huang

Publication date: 20 June 2012

Published in: International Journal of Wavelets, Multiresolution and Information Processing (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1142/s021969131100447x

zbMATH Keywords

integral operator; stochastic gradient descent; coefficient regularization; learning rate

Mathematics Subject Classification ID

62J02: General nonlinear regression

68T05: Learning and adaptive systems in artificial intelligence

Related Items

ELASTIC-NET REGULARIZATION FOR LOW-RANK MATRIX RECOVERY

Cites Work

• Unnamed Item
• Model selection for regularized least-squares algorithm in learning theory
• Fully online classification by regularization
• Learning with sample dependent hypothesis spaces
• Application of integral operator for regularized least-square regression
• Learning gradients by a gradient descent algorithm
• Online learning algorithms
• Learning rates of gradient descent algorithm for classification
• Shannon sampling. II: Connections to learning theory
• Learning theory estimates via integral operators and their approximations
• On early stopping in gradient descent learning
• COMPRESSED SENSING BY ITERATIVE THRESHOLDING OF GEOMETRIC WAVELETS: A COMPARING STUDY
• LOCAL LEARNING ESTIMATES BY INTEGRAL OPERATORS
• Online Regularized Classification Algorithms
• ON AN EFFICIENT SPARSE REPRESENTATION OF OBJECTS OF GENERAL SHAPE VIA CONTINUOUS EXTENSION AND WAVELET APPROXIMATION
• Remarks on Inequalities for Large Deviation Probabilities
• SVM Soft Margin Classifiers: Linear Programming versus Quadratic Programming
• Sparsity and incoherence in compressive sampling