Learning curve (machine learning)
In machine learning, a learning curve is a graphical representation that shows how a model's performance on a Training, [validation, and test data sets|training set] changes with the number of training iterations or the amount of training data.
Typically, the number of training epochs or training set size is plotted on the x-axis, and the value of the loss function on the y-axis.
Synonyms include error curve, experience curve, improvement curve and generalization curve.
More abstractly, learning curves plot the difference between learning effort and predictive performance, where "learning effort" usually means the number of training samples, and "predictive performance" means accuracy on testing samples.
Learning curves have many useful purposes in ML, including:
- choosing model parameters during design,
- adjusting optimization to improve convergence,
- and diagnosing problems such as overfitting.
Formal definition
When creating a function to approximate the distribution of some data, it is necessary to define a loss function to measure how good the model output is. We then define an optimization process which finds model parameters such that is minimized, referred to as.Training curve for amount of data
If the training data isand the validation data is
a learning curve is the plot of the two curves