Wouter M. Koolen
Titel
Citeras av
Citeras av
År
Follow the leader if you can, hedge if you must
S De Rooij, T Van Erven, PD Grünwald, WM Koolen
The Journal of Machine Learning Research 15 (1), 1281-1316, 2014
1212014
Hedging Structured Concepts.
WM Koolen, MK Warmuth, J Kivinen
COLT, 93-105, 2010
942010
Second-order quantile methods for experts and combinatorial games
WM Koolen, T Van Erven
Conference on Learning Theory, 1155-1175, 2015
622015
Universal codes from switching strategies
WM Koolen, S de Rooij
IEEE Transactions on Information Theory 59 (11), 7168-7185, 2013
52*2013
A closer look at adaptive regret
D Adamskiy, WM Koolen, A Chernov, V Vovk
International Conference on Algorithmic Learning Theory, 290-304, 2012
522012
Metagrad: Multiple learning rates in online learning
T van Erven, WM Koolen
Advances in Neural Information Processing Systems, 3666-3674, 2016
382016
Adaptive hedge
TV Erven, WM Koolen, SD Rooij, P Grünwald
Advances in Neural Information Processing Systems, 1656-1664, 2011
332011
Putting Bayes to sleep.
WM Koolen, D Adamskiy, MK Warmuth
NIPS, 135-143, 2012
262012
Maximin action identification: A new bandit framework for games
A Garivier, E Kaufmann, WM Koolen
Conference on Learning Theory, 1028-1050, 2016
252016
Mixture martingales revisited with applications to sequential tests and confidence intervals
E Kaufmann, W Koolen
arXiv preprint arXiv:1811.11419, 2018
232018
Monte-Carlo tree search by best arm identification
E Kaufmann, WM Koolen
Advances in Neural Information Processing Systems, 4897-4906, 2017
222017
Combining adversarial guarantees and stochastic fast rates in online learning
WM Koolen, P Grünwald, T van Erven
Advances in Neural Information Processing Systems, 4457-4465, 2016
222016
Learning the learning rate for prediction with expert advice
WM Koolen, T Van Erven, P Grünwald
Advances in neural information processing systems, 2294-2302, 2014
222014
Minimax time series prediction
WM Koolen, A Malek, PL Bartlett, YA Yadkori
Advances in Neural Information Processing Systems, 2557-2565, 2015
172015
The Pareto regret frontier
WM Koolen
Advances in Neural Information Processing Systems, 863-871, 2013
152013
A closer look at adaptive regret
D Adamskiy, WM Koolen, A Chernov, V Vovk
The Journal of Machine Learning Research 17 (1), 706-726, 2016
142016
Putting Bayes to sleep
D Adamskiy, MKK Warmuth, WM Koolen
Advances in neural information processing systems, 135-143, 2012
142012
Minimax fixed-design linear regression
PL Bartlett, WM Koolen, A Malek, E Takimoto, MK Warmuth
Conference on Learning Theory, 226-239, 2015
132015
Efficient minimax strategies for square loss games
WM Koolen, A Malek, PL Bartlett
Advances in Neural Information Processing Systems, 3230-3238, 2014
132014
Combining Strategies Efficiently: High-Quality Decisions from Conflicting Advice
WM Koolen
132011
Systemet kan inte utföra åtgärden just nu. Försök igen senare.
Artiklar 1–20