Timezone: »

New Adaptive Algorithms for Online Classification
Francesco Orabona · Yacov Crammer

Wed Dec 08 12:00 AM -- 12:00 AM (PST) @ None #None

We propose a general framework to online learning for classification problems with time-varying potential functions in the adversarial setting. This framework allows to design and prove relative mistake bounds for any generic loss function. The mistake bounds can be specialized for the hinge loss, allowing to recover and improve the bounds of known online classification algorithms. By optimizing the general bound we derive a new online classification algorithm, called NAROW, that hybridly uses adaptive- and fixed- second order information. We analyze the properties of the algorithm and illustrate its performance using synthetic dataset.

Author Information

Francesco Orabona (Boston University)
Yacov Crammer (Technion)

More from the Same Authors