Analysis of Two Gradient-Based Algorithms for On-Line Regression

This publication has 15 references indexed in Scilit:

• Predicting a binary sequence almost as well as the optimal biased coin
  Information and Computation, 2003
• Relative Loss Bounds for Multidimensional Regression Problems
  Machine Learning, 2001
• General Convergence Results for Linear Discriminant Updates
  Machine Learning, 2001
• How to use expert advice
  Journal of the ACM, 1997
• Exponentiated Gradient versus Gradient Descent for Linear Predictors
  Information and Computation, 1997
• Worst-case quadratic loss bounds for prediction using linear functions and gradient descent
  IEEE Transactions on Neural Networks, 1996
• Decision theoretic generalizations of the PAC model for neural net and other learning applications
  Information and Computation, 1992
• Universal prediction of individual sequences
  IEEE Transactions on Information Theory, 1992
• Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm
  Machine Learning, 1988
• Probability Inequalities for Sums of Bounded Random Variables
  Journal of the American Statistical Association, 1963