156 citations · 950 across the 61 of their papers we have counts for
6 papers · 1 filter
Data-dependent kernels in nearly-linear time
Guy Lever, Tom Diethe, John Shawe-Taylor
We propose a method to efficiently construct data-dependent kernels which can make use of large quantities of (unlabeled) data. Our construction makes an approximation in the stand…
PAC-Bayesian Inequalities for Martingales
Yevgeny Seldin, François Laviolette, Nicolò Cesa-Bianchi +2
We present a set of high-probability inequalities that control the concentration of weighted averages of multiple (possibly uncountably many) simultaneously evolving and interdepen…
PAC-Bayes-Bernstein Inequality for Martingales and its Application to Multiarmed Bandits
Yevgeny Seldin, Nicolò Cesa-Bianchi, Peter Auer +2
We develop a new tool for data-dependent analysis of the exploration-exploitation trade-off in learning under limited feedback. Our tool is based on two main ingredients. The first…
A Note on Improved Loss Bounds for Multiple Kernel Learning
Zakria Hussain, John Shawe-Taylor, Mario Marchand
In this paper, we correct an upper bound, presented in~\cite{hs-11}, on the generalisation error of classifiers learned through multiple kernel learning. The bound in~\cite{hs-11}…
PAC-Bayesian Analysis of the Exploration-Exploitation Trade-off
Yevgeny Seldin, Nicolò Cesa-Bianchi, François Laviolette +3
We develop a coherent framework for integrative simultaneous analysis of the exploration-exploitation and model order selection trade-offs. We improve over our preceding results on…
PAC-Bayesian Analysis of Martingales and Multiarmed Bandits
Yevgeny Seldin, François Laviolette, John Shawe-Taylor +2
We present two alternative ways to apply PAC-Bayesian analysis to sequences of dependent random variables. The first is based on a new lemma that enables to bound expectations of c…