Solving large scale linear prediction problems using stochastic gradient descent algorithms
Solving large scale linear prediction problems using stochastic gradient descent algorithms
Tong Zhang
2004 · DOI: 10.1145/1015330.1015332
International Conference on Machine Learning · 1,221 Citations
TLDR
Stochastic gradient descent algorithms on regularized forms of linear prediction methods, related to online algorithms such as perceptron, are studied, and numerical rate of convergence for such algorithms is obtained.