Tim van Erven
Tim van Erven
Associate professor at the University of Amsterdam, the Netherlands
Verified email at uva.nl - Homepage
Cited by
Cited by
R\'enyi Divergence and Kullback-Leibler Divergence
T Van Erven, P Harremoës
IEEE Transactions on Information Theory 60 (7), 3797-3820, 2014
Follow the leader if you can, hedge if you must
S de Rooij, T Van Erven, PD Grünwald, WM Koolen
Journal of Machine Learning Research 15, 1281-1316, 2014
Catching up faster by switching sooner: a predictive approach to adaptive estimation with an application to the AIC-BIC dilemma [with Discussion]
T Van Erven, P Grünwald, S De Rooij
Journal of the Royal Statistical Society. Series B (Statistical Methodology …, 2012
A second-order bound with excess losses
P Gaillard, G Stoltz, T Van Erven
Conference on Learning Theory, 176-196, 2014
Second-order quantile methods for experts and combinatorial games
WM Koolen, T Van Erven
Conference on Learning Theory, 1155-1175, 2015
Fast rates in statistical and online learning
T Van Erven, P Grunwald, NA Mehta, M Reid, R Williamson
MIT Press, 2015
Rényi divergence and majorization
T van Erven, P Harremoës
2010 IEEE International Symposium on Information Theory, 1335-1339, 2010
Metagrad: Multiple learning rates in online learning
T van Erven, WM Koolen
arXiv preprint arXiv:1604.08740, 2016
Follow the leader with dropout perturbations
T Van Erven, W Kotłowski, MK Warmuth
Conference on Learning Theory, 949-974, 2014
Catching Up Faster in Bayesian Model Selection and Model Averaging.
T Van Erven, P Grunwald, S De Rooij
NIPS 20, 417-424, 2007
Game-theoretically optimal reconciliation of contemporaneous hierarchical time series forecasts
T Van Erven, J Cugliari
Modeling and stochastic learning for forecasting in high dimensions, 297-317, 2015
Combining adversarial guarantees and stochastic fast rates in online learning
WM Koolen, P Grünwald, T van Erven
arXiv preprint arXiv:1605.06439, 2016
Adaptive hedge
T Erven, WM Koolen, S Rooij, P Grünwald
Advances in Neural Information Processing Systems 24, 1656-1664, 2011
Learning the learning rate for prediction with expert advice
W Koolen, T Van Erven, P Grunwald
Advances in Neural Information Processing Systems 27 (NIPS 2014), 2294-2302, 2014
Mixability is Bayes Risk Curvature Relative to Log Loss
T van Erven, MD Reid, RC Williamson
The Journal of Machine Learning Research, 1639-1663, 2012
Learning the switching rate by discretising Bernoulli sources online
S Rooij, T Erven
Artificial Intelligence and Statistics, 432-439, 2009
Mixability in statistical learning
T Van Erven, PD Grünwald, MD Reid, RC Williamson
Advances in Neural Information Processing Systems 25 (NIPS 2012), 2012
Pac-bayes mini-tutorial: a continuous union bound
T van Erven
arXiv preprint arXiv:1405.1580, 2014
Adaptive hedge
T Van Erven, P Grünwald, WM Koolen, S De Rooij
arXiv preprint arXiv:1110.6416, 2011
When data compression and statistics disagree: two frequentist challenges for the minimum description length principle
TAL van Erven
Mathematical Institute, Faculty of Science, Leiden, 2010
The system can't perform the operation now. Try again later.
Articles 1–20