Many of the training set based bounds effectively reduce the value of by some fixed amount. The program ’bound’ will automatically reduce the value of with two arguments.
Each of these arguments acts independently to reduce the value of . The value of will only be reduced on training example based bounds. There are two more arguments necessary for application of one of the simple training set based bound:
Here is an application of a simple training set based bound:
12:07AM z-26: cat train_error
train_examples 100 train_errors 3 log_prior -50 delta 0.3 12:07AM z-27: bound train_error Applying varying approximation tail bound delta 0.3 lower_delta 0.5 train_examples 100 train_errors 3 log_hypothesis_size 0 log_prior -50 approximation automatic true_error = 0.03 0.466502545401 9.31322574615e-10 |