Peter Auer's Publications

This list is also available as BiBTeX file.

[1]: P. Auer, H. Burgsteiner, and W. Maass. A learning rule for very simple universal approximators consisting of a single layer of perceptrons. Neural Networks, 2007. in press. .
[2]: P. Auer, N. Cesa-Bianchi, Y. Freund, and R. E. Schapire. The nonstochastic multiarmed bandit problem. SIAM Journal on Computing, 32(1):48-77, 2002. A preliminary version has appeared in Proceedings of the 36th Annual Symposium on Foundations of Computer Science.
[3]: P. Auer, N. Cesa-Bianchi, and C. Gentile. Adaptive and self-confident on-line learning algorithms. JCSS, 64(1):48-75, 2002. A preliminary version has appeared in Proc. 13th Ann. Conf. Computational Learning Theory.
[4]: P. Auer, N. Cesa-Bianchi, and P. Fischer. Finite time analysis of the multiarmed bandit problem. Machine Learning, 47(2/3):235-256, 2002. A preliminary version has appeared in Proc. of the 15th International Conference on Machine Learning.
[5]: P. Auer, H. Burgsteiner, and W. Maass. Reducing communication for distributed learning in neural networks. In José R. Dorronsoro, editor, Proc. of the International Conference on Artificial Neural Networks -- ICANN 2002, volume 2415 of Lecture Notes in Computer Science, pages 123-128. Springer, 2002. . .
[6]: P. Auer. Using confidence bounds for exploitation-exploration trade-offs. J. Machine Learning Research, 3(Nov):397-422, 2002. A preliminary version has appeared in Proc. of the 41th Annual Symposium on Foundations of Computer Science.
[7]: P. Auer. Why students don't ask questions. TELEMATIK, 8(1):21-23, 2002. Special Issue on Foundations of Information Processing for the 21st Century.
[8]: K. Andrews, W. Kienreich, V. Sabol, J. Becker, G. Droschl, F. Kappe, M. Granitzer, P. Auer, and K. Tochtermann. The InfoSky visual explorer: exploiting hierarchical structure and document similarities. Information Visualization, 1:166-181, 2002.
[9]: P. Auer and C. Gentile. Adaptive and self-confident on-line learning algorithms. In Proc. 13th Ann. Conf. Computational Learning Theory, pages 107-117. Morgan Kaufmann, 2000.
[10]: P. Auer. An improved on-line algorithm for learning linear evaluation functions. In Proc. 13th Ann. Conf. Computational Learning Theory, pages 118-125. Morgan Kaufmann, 2000.
[11]: P. Auer. Using upper confidence bounds for online learning. In Proceedings of the 41th Annual Symposium on Foundations of Computer Science, pages 270-293. IEEE Computer Society, 2000.
[12]: P. Auer and P. M. Long. Structural results about on-line learning models with and without queries. Machine Learning, 36:147-181, 1999. A preliminary version has appeared in Proceedings of the 26th ACM Symposium on the Theory of Computing.
[13]: P. Auer, N. Cesa-Bianchi, and P. Fischer. Finite time analysis of the multiarmed bandit problem. In IT Workshop on Decision, Estimation, Classification and Imaging, Santa Fe, Feb 1999.
[14]: P. Auer and M. K. Warmuth. Tracking the best disjunction. Machine Learning, 32:127-150, 1998. A preliminary version has appeared in Proceedings of the 36th Annual Symposium on Foundations of Computer Science.
[15]: P. Auer and W. Maass. Introduction to the special issue on computational learning theory. Algorithmica, 22(1/2):1-2, 1998.
[16]: P. Auer, P. M. Long, and A. Srinivasan. Approximating hyper-rectangles: Learning and pseudorandom sets. Journal of Computer and System Sciences, 57(3):376-388, 1998. A preliminary version has appeared in Proc. 29th Ann. Symp. Theory of Computing.
[17]: P. Auer and N. Cesa-Bianchi. On-line learning with malicious noise and the closure algorithm. Annals of Mathematics and Artificial Intelligence, 23:83-99, 1998. A preliminary version has appeared in Lecture Notes in Artificial Intelligence 872, Springer.
[18]: P. Auer. On learning from ambiguous information. Periodica Polytechnica Electrical Engineering, 42(1):115-122, 1998.
[19]: P. Auer. Some thoughts on boosting and neural networks. In L. Cromme, T. Kolb, and H. Koch, editors, Beiträge zum 3. Cottbuser Workshop `Aspekte des Neuronalen Lernens' CoWAN'98, pages 11-28, Cottbus, Germany, October 1998. Shaker Verlag. Invited paper.
[20]: J. Kivinen, M. K. Warmuth, and P. Auer. The perceptron algorithm vs. Winnow: linear vs. logarithmic mistake bounds when few input variables are relevant. Artificial Intelligence, pages 325-343, 1997.
[21]: P. Auer, P. M. Long, and A. Srinivasan. Approximating hyper-rectangles: Learning and pseudo-random sets. In Proc. 29th Ann. Symp. Theory of Computing, pages 314-323. ACM, May 1997.
[22]: P. Auer. Learning nested differences in the presence of malicious noise. Theoretical Computer Science, 185:159-175, 1997. A preliminary version has appeared in Proceedings of the 6th International Workshop on Algorithmic Learning Theory, ALT`95.
[23]: P. Auer. On learning from multi-instance examples: Empirical evaluation of a theoretical approach. In D. H. Fisher, editor, Proc. 14th Int. Conf. Machine Learning, pages 21-29. Morgan Kaufmann, 1997.
[24]: P. Auer, S. Kwek, W. Maass, and M. K. Warmuth. Learning of depth two neural nets with constant fan-in at the hidden nodes. In Proc. of the 9th Conference on Computational Learning Theory 1996, pages 333-343. ACM-Press (New York), 1996. . .
[25]: P. Auer and K. Hornik. The number of points of an empirical or Poisson process covered by unions of sets. Journal of Multivariate Analysis, 57:37-51, 1996.
[26]: P. Auer and K. Hornik. Limit laws for the maximal and minimal increments of the Poisson process. Studia Scientiarum Mathematicarum Hungarica, 31:1-13, 1996.
[27]: P. Auer, M. Herbster, and M. K. Warmuth. Exponentially many local minima for single neurons. In D. S. Touretzky, M. C. Mozer, and M. E. Hasselmo, editors, Advances in Neural Information Processing Systems 8, pages 316-322. MIT Press, 1996.
[28]: P. Auer, P. Caianiello, and N. Cesa-Bianchi. Tight bounds on the cumulative profit of distributed voters. In Proceedings of the 15th Annual ACM Symposium on Principles of Distributed Computing, page 312, 1996. Abstract.
[29]: P. Auer and M. K. Warmuth. Tracking the best disjunction. In Proceedings of the 36th Annual Symposium on Foundations of Computer Science, pages 312-321. IEEE Computer Society Press, 1995.
[30]: P. Auer, P. M. Long, W. Maass, and G. J. Wöginger. On the complexity of function learning. Machine Learning, 18:187-230, 1995. Invited paper in a special issue of Machine Learning.
[31]: P. Auer, R. C. Holte, and W. Maass. Theory and applications of agnostic PAC-learning with small decision trees. In Proc. of the 12th International Machine Learning Conference, Tahoe City (USA), pages 21-29. Morgan Kaufmann (San Francisco), 1995. . .
[32]: P. Auer, N. Cesa-Bianchi, Y. Freund, and R. E. Schapire. Gambling in a rigged casino: The adversarial multi-armed bandit problem. In Proceedings of the 36th Annual Symposium on Foundations of Computer Science, pages 322-331. IEEE Computer Society Press, Los Alamitos, CA, 1995.
[33]: P. Auer. Learning nested differences in the presence of malicious noise. In Klaus P. Jantke, Takeshi Shinohara, and Thomas Zeugmann, editors, 6th International Workshop, ALT`95, Proceedings, pages 123-137. Springer, 1995. LNAI 997.
[34]: K. Hornik, M. Stinchcombe, H. White, and P. Auer. Degree of approximation results for feedforward networks approximating unknown mappings and their derivatives. Neural Computation, 6:1262-1275, 1994.
[35]: P. Auer and P. M. Long. Simulating access to hidden information while learning. In Proceedings of the 26th Annual ACM Symposium on the Theory of Computing, pages 263-272. ACM Press, 1994.
[36]: P. Auer and K. Hornik. On the number of points of a homogeneous Poisson process. Journal of Multivariate Analysis, 48(1):115-156, 1994.
[37]: P. Auer and N. Cesa-Bianchi. On-line learning with malicious noise and the closure algorithm. In Setsuo Arikawa and Klaus P. Jantke, editors, Algorithmic Learning Theory, AII'94, ALT'94, pages 229-247. Lecture Notes in Artificial Intelligence 872, Springer, 1994.
[38]: P. Auer, P. M. Long, W. Maass, and G. J. Wöginger. On the complexity of function learning. In Proceedings of the 5th Annual ACM Conference on Computational Learning Theory, pages 392-401, 1993.
[39]: P. Auer. On-line learning of rectangles in noisy environments. In Proceedings of the Sixth Annual ACM Conference on Computational Learning Theory, pages 253-261. ACM Press, New York, NY, 1993.
[40]: P. Auer, K. Hornik, and P. Révész. Some limit theorems for the homogeneous Poisson process. Statistics & Probability Letters, 12:91-96, 1991.
[41]: P. Auer. Unification in the combination of disjoint theories. In Word Equations and Related Topics, pages 177-186. Lecture Notes of Computer Science 677, Springer, 1991.
[42]: P. Auer. Solving string equations with constant restrictions. In Word Equations and Related Topics, pages 103-132. Lecture Notes of Computer Science 677, Springer, 1991.
[43]: P. Auer. The circle homogeneously covered by random walk on Z². Statistics & Probability Letters, 9:403-407, 1990.
[44]: P. Auer and P. Révész. On the relative frequency of points visited by random walk on Z². In Colloquia Mathematica Societatis Janos Bolai, 57. Limit Theorem in Probability and Statistics, Pecs (Hungary), pages 27-33, 1989.
[45]: P. Auer. Some hitting probabilities of random walks on Z². In Colloquia Mathematica Societatis Janos Bolai, 57. Limit Theorem in Probability and Statistics, Pecs (Hungary), pages 9-25, 1989.