56 search results - page 3 / 12 » Stochastic methods for l1 regularized loss minimization |
JMLR
2010
13 years 24 days ago
2010
We consider regularized stochastic learning and online optimization problems, where the objective function is the sum of two convex terms: one is the loss function of the learning...
NIPS
1996
13 years 7 months ago
1996
In this paper we apply the method of complexity regularization to derive estimation bounds for nonlinear function estimation using a single hidden layer radial basis function netwo...
ANOR
2010
13 years 6 months ago
2010
Many image denoising methods can be characterized as minimizing "loss + penalty," where the "loss" measures the fidelity of the denoised image to the data, and ...
ML
2010
ACM
13 years 24 days ago
2010
ACM
Traditional classification methods assume that the training and the test data arise from the same underlying distribution. However, in several adversarial settings, the test set is...
JMLR
2010
13 years 4 months ago
2010
A wide variety of machine learning problems can be described as minimizing a regularized risk functional, with different algorithms using different notions of risk and differen...