Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
We prove that every online learnable class of functions of Littlestone dimension d admits a learning algorithm with finite information complexity. Towards this end, we use the notion of a globally stable algorithm. Generally, the information complexity of such a globally stable algorithm is large yet finite, roughly exponential in d. We also show there is room for improvement; for a canonical online learnable class, indicator functions of affine subspaces of dimension d, the information complexity can be upper bounded logarithmically in d.
Maryam Kamgarpour, Andreas Krause, Ilija Bogunovic
Giancarlo Ferrari Trecate, Muhammad Zakwan, Liang Xu