Abstract
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.
Original language | English (US) |
---|---|
Pages (from-to) | 1096-1114 |
Number of pages | 19 |
Journal | Journal of Machine Learning Research |
Volume | 49 |
Issue number | June |
State | Published - Jun 6 2016 |
Event | 29th Conference on Learning Theory, COLT 2016 - New York, United States Duration: Jun 23 2016 → Jun 26 2016 |
All Science Journal Classification (ASJC) codes
- Software
- Control and Systems Engineering
- Statistics and Probability
- Artificial Intelligence