Continual learning aims to improve the ability of modern learning systems todeal with non-stationary distributions, typically by attempting to learn a seriesof tasks sequentially.

We therefore assume that the algorithm has access to an oracle that knows intuitively what it means to be fair, but cannot explicitly enunciate the fairness metric.

Medicalsubjectheadings (mesh).Bulletinofthe Medical Library Association, 88(3):265, 2000.

However, this will lead to an intractable number of hyperparameters.

Namely,thattheempirical lossofall the functions in the class is -close to the true loss. Finally, we develop a set of tools for calculating the approximate description length of classes of functions that can be presented as a composition of linear function classes and non-linear functions.

The formal definition of MF-MAB is presented in Section 2. 1.1 Contributions