In statistical learning theory generalisation error is a measure how

well a predictive of a learning algorithm perform on unseen dataset. The expected error is approximately equivalent

to the empirical error and the error reduces when we increase the dataset. Since

the generalisation of the learning algorithm is done using randomly drawn from

a finite independent and identically distributed samples the model might be

sensitive. One way of overcoming this problem is by relating the

training(given) error to the generalisation error – which possibly would avoid

overfitting.

There are many theories for

generalisation error – each theory has strengths and weaknesses.