10054 search results - page 89 / 2011 » On the Complexity of Function Learning |
120
Voted
JMLR
2010
14 years 11 months ago
2010
We extend the well-known BFGS quasi-Newton method and its memory-limited variant LBFGS to the optimization of nonsmooth convex objectives. This is done in a rigorous fashion by ge...
88
Voted
PERCOM
2006
ACM
16 years 1 days ago
2006
ACM
This paper proposes a distributed platform designed to support pervasive learning and interactivity on a university campus and to ease tasks related to learning and teaching. The ...
107
click to vote
MOC
2011
14 years 7 months ago
2011
We present an asymptotically fast algorithm for the numerical evaluation of modular functions such as the elliptic modular function j. Our algorithm makes use of the natural connec...
118
Voted
ICML
2004
IEEE
15 years 5 months ago
2004
IEEE
This paper introduces RankOpt, a linear binary classifier which optimises the area under the ROC curve (the AUC). Unlike standard binary classifiers, RankOpt adopts the AUC stat...
115
Voted
JMLR
2008
15 years 13 days ago
2008
The computational complexities arising in motor control can be ameliorated through the use of a library of motor synergies. We present a new model, referred to as the Greedy Addit...