Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

November 15, 1998, Vol. 10, No. 8, Pages 2201-2217
(doi: 10.1162/089976698300017034)
© 1998 Massachusetts Institute of Technology
Online Learning from Finite Training Sets and Robustness to Input Bias
Article PDF (193.63 KB)
Abstract

We analyze online gradient descent learning from finite training sets at noninfinitesimal learning rates η. Exact results are obtained for the time-dependent generalization error of a simple model system: a linear network with a large number of weights N, trained on p = αN examples. This allows us to study in detail the effects of finite training set size α on, for example, the optimal choice of learning rate η. We also compare online and offline learning, for respective optimal settings of η at given final learning time. Online learning turns out to be much more robust to input bias and actually outperforms offline learning when such bias is present; for unbiased inputs, online and offline learning perform almost equally well.