107 search results - page 12 / 22 » General Loss Bounds for Universal Sequence Prediction |
SIGECOM
2010
ACM
14 years 5 days ago
2010
ACM
We explore the striking mathematical connections that exist between market scoring rules, cost function based prediction markets, and no-regret learning. We first show that any c...
ICCV
2011
IEEE
12 years 7 months ago
2011
IEEE
Most existing techniques for analyzing face images assume that the faces are at near-frontal poses. Generalizing to non-frontal faces is often difficult, due to a dearth of groun...
25
Voted
COLT
2001
Springer
13 years 12 months ago
2001
Springer
In this paper, we examine on-line learning problems in which the target concept is allowed to change over time. In each trial a master algorithm receives predictions from a large ...
PKDD
2010
Springer
13 years 5 months ago
2010
Springer
Prior knowledge, in the form of simple advice rules, can greatly speed up convergence in learning algorithms. Online learning methods predict the label of the current point and the...
PODC
2009
ACM
14 years 8 months ago
2009
ACM
d Abstract] Prosenjit Bose School of Computer Science Carleton University Ottawa, Canada jit@scs.carleton.ca Paz Carmi Dept. of Computer Science Ben-Gurion Univ. of the Negev Beer-...