*This is an advanced course in learning theory.*

The probably approximately correct (PAC) theory has been the standard framework of machine learning for decades, but its underlying “i.i.d. data” assumption results in a significant theory-practice gap. This course introduces online learning theory, whose probability-free nature naturally avoids the aforementioned theory-practice gap. The main focuses are:
- Learning with expert advice.
- Online convex optimization.
- Individual sequence prediction.
- Convergence to equilibria in repeated games.
The tentative schedule can be found below.

The exact contents of this course may change with respect to the latest advances
in learning theory.