Worst-case quadratic loss bounds for prediction using linear functions and gradient descent

10.1017/CBO9781139172011

haykin, 1991, Adaptive Filter Theory

10.1017/CBO9780511810817

10.1109/72.80346

kaczmarz, 1937, angenaherte auflo¨sung von systemen linearer gleichungen, Bull Acad Polon Sci Lett A, 35, 355

10.1145/130385.130402

kivinen, 1994, Exponentiated gradient versus gradient descent for linear predictors

10.1007/BF00116827

littlestone, 1989, Mistake Bounds and Logarithmic Linear&#x2010 threshold Learning Algorithms

10.1145/103418.103467

10.1002/j.1538-7305.1966.tb00020.x

10.2307/2981683

widrow, 0, adaptive switching circuits, Proc 1960 IRE WESCON Conv Rec, 96

10.1016/B978-1-55860-146-8.50032-1

10.1145/167088.167198

faber, 1991, applications of learning theorems, Fundamenta Informaticae, 15, 145, 10.3233/FI-1991-15205

widrow, 1985, Adaptive Signal Processing

duda, 1973, Pattern Classification and Scene Analysis

golub, 1990, Matrix Computations

10.1109/18.144706

10.1109/18.256500

10.1007/BF00116828

hardle, 1991, Smoothing Techniques, 10.1007/978-1-4612-4432-5

luenberger, 1984, Linear and Nonlinear Programming

10.1145/130385.130430

littlestone, 1991, the weighted majority algorithm

mycielski, 1988, a learning algorithm for linear operators, Proc Amer Math Soc, 103, 547, 10.1090/S0002-9939-1988-0943082-5

mycielski, 1991, General learning theorems

10.1109/PROC.1980.11774

10.1002/j.1538-7305.1967.tb04231.x