Department Mathematics and Information Technology
Organisational unit: Departments and Institutes
Research output
- Published
Logarithmic online regret bounds for undiscounted reinforcement learning
Auer, P. & Ortner, R., 2007, Advances in Neural Information Processing Systems 19. MIT Press, p. 49-56Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
- Published
Approximating Hyper-Rectangles: Learning and Pseudo-random Sets
Auer, P., Long, P. M. & Srinivasan, A., 1997, Proc. 29th Ann. Symp. Theory of Computing. p. 314-323Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
- Published
Adaptive and self-confident online learning algorithms
Auer, P., Cesa-Bianchi, N. & Gentile, C., 2002, In: Journal of computer and system sciences (JCSS). 64, p. 48-78Research output: Contribution to journal › Article › Research › peer-review
- Published
Relevance Feedback Models for Content-Based Image Retrieval
Auer, P. & Leung, P., 2009, Multimedia Analysis, Processing and Communications.Research output: Chapter in Book/Report/Conference proceeding › Chapter › Research
- Published
The Perceptron algorithm vs. Winnow: linear vs. logarithmic mistake bounds when few input variables are relevant
Auer, P., Kivinen, J. & Warmuth, M. K., 1997, In: Artificial intelligence. p. 325-343Research output: Contribution to journal › Article › Research › peer-review
- Published
On the Complexity of Function Learning
Auer, P., Long, P. M., Maass, W. & Wöginger, G. J., 1993, Sixth Annual ACM Conference on Computational Learning Theory (COLT 1993). p. 392-401Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
- Published
Some thoughts on Boosting and Neural Networks
Auer, P., 1998, 3. Cottbuser Workshop "Aspekte des Neuronalen Lernens". p. 11-28Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
- Published
Near-optimal Regret Bounds for Reinforcement Learning
Auer, P., Jaksch, T. & Ortner, R., 2009, Advances in neural information processing systems 21. MIT Press, p. 89-96Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
- Published
UCB Revisited: Improved Regret Bounds for the Stochastic Multi-Armed Bandit Problem
Auer, P. & Ortner, R., 2010, In: Periodica Mathematica Hungarica. 61, p. 55-65Research output: Contribution to journal › Article › Research › peer-review
- Published
Near-optimal Regret Bounds for Reinforcement Learning
Auer, P., Jaksch, T. & Ortner, R., 2008.Research output: Contribution to conference › Poster › Research › peer-review
