We consider the problem of prediction with expert advice when the losses of the experts have low-dimensional structure: they are restricted to an unknown d-dimensional subspace. We devise algorithms with regret bounds that are independent of the number of experts and depend only on the rank d. For the stochastic model we show a tight bound of Θp√ dTq, and extend it to a setting of an approximate d subspace. For the adversarial model we show an upper bound of Opd√ Tq and a lower bound of Ωp√ dTq.
All Science Journal Classification (ASJC) codes
- Artificial Intelligence
- Control and Systems Engineering
- Statistics and Probability