15 search results - page 3 / 3 » Improved Risk Tail Bounds for On-Line Algorithms |
ESA
2007
Springer
14 years 1 months ago
2007
Springer
We study the online ad-auctions problem introduced by Mehta et. al. [15]. We design a (1 − 1/e)competitive (optimal) algorithm for the problem, which is based on a clean primal-...
ICML
2009
IEEE
14 years 8 months ago
2009
IEEE
Recent approaches to learning structured predictors often require approximate inference for tractability; yet its effects on the learned model are unclear. Meanwhile, most learnin...
SIGMETRICS
2011
ACM
12 years 10 months ago
2011
ACM
The massive data streams observed in network monitoring, data processing and scientific studies are typically too large to store. For many applications over such data, we must ob...
EMNLP
2011
12 years 7 months ago
2011
Log-linear parsing models are often trained by optimizing likelihood, but we would prefer to optimise for a task-specific metric like Fmeasure. Softmax-margin is a convex objecti...
SDM
2008
SIAM
13 years 8 months ago
2008
SIAM
This paper presents a stagewise least square (SLS) loss function for classification. It uses a least square form within each stage to approximate a bounded monotonic nonconvex los...