683 search results - page 94 / 137 » Generalization Bounds for Learning Kernels |
TNN
2011
13 years 4 months ago
2011
Domain adaptation solves a learning problem in a target domain by utilizing the training data in a different but related source domain. Intuitively, discovering a good feature rep...
COLT
2004
Springer
14 years 3 months ago
2004
Springer
Abstract— We prove that given a nearly log-concave distribution, in any partition of the space to two well separated sets, the measure of the points that do not belong to these s...
SIAMJO
2010
13 years 4 months ago
2010
We study the problem of minimizing the expected loss of a linear predictor while constraining its sparsity, i.e., bounding the number of features used by the predictor. While the r...
SIGECOM
2010
ACM
14 years 2 months 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...
QEST
2010
IEEE
13 years 7 months ago
2010
IEEE
The method of stochastic state classes approaches the analysis of Generalised Semi Markov Processes (GSMP) through symbolic derivation of probability density functions over Differe...