Abstract--Kernel-based algorithms such as support vector machines have achieved considerable success in various problems in batch setting, where all of the training data is availab...
Jyrki Kivinen, Alex J. Smola, Robert C. Williamson
This paper provides a probabilistic derivation of an identity connecting the square loss of ridge regression in on-line mode with the loss of a retrospectively best regressor. Some...
In this paper, we are interested in the analysis of regularized online algorithms associated with reproducing kernel Hilbert spaces. General conditions on the loss function and st...
This paper considers the least-square online gradient descent algorithm in a reproducing kernel Hilbert space (RKHS) without explicit regularization. We present a novel capacity i...
We study online learning when individual instances are corrupted by adversarially chosen random noise. We assume the noise distribution is unknown, and may change over time with n...