[1]

Peter Auer and Alex P. Leung. Relevance feedback models for content-based image retrieval. In Multimedia Analysis, Processing and Communications, Springer, 2010.

[2]

Peter Auer and Ronald Ortner. Ucb revisited: Improved regret bounds for the stochastic multi-armed bandit problem. Periodica Mathematica Hungarica, 61(1-2):55 – 65, 2010.

[3]

Peter Auer, Zakria Hussain, Samuel Kaski, Arto Klami, Jussi Kujala, Jorma Laaksonen, Alex P. Leung, Kitsuchart Pasupa, and John Shawe-Taylor. Pinview: Implicit feedback in content-based image retrieval. In To appear in JMLR: Workshop and Conference Proceedings, 2010.

[4]

Zakria Hussain, Alex P. Leung, Kitsuchart Pasupa, David R. Hardoon, Peter Auer, and John Shawe-Taylor. Exploration-exploitation of eye movement enriched multiple feature spaces for content-based image retrieval. In European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), Barcelona, Spain, 2010.

[5]

Thomas Jaksch, Ronald Ortner, and Peter Auer. Near-optimal regret bounds for reinforcement learning. Journal of Machine Learning Research, 11:1563–1600, 2010.

[6]

Martin Antenreiter, Ronald Ortner, and Peter Auer. Combining classifiers for improved multilabel image classification. In Learning from Multi-label Data, MLD Workshop at ECML 2009, pages 16–27, 2009.

[7]

Peter Auer, Thomas Jaksch, and Ronald Ortner. Near-optimal regret bounds for reinforcement learning. In Y. Bengio D. Koller, D. Schuurmans and L. Bottou, editors, Advances in neural information processing systems 21, pages 89 – 96, 2009. (PDF)

[8]

Johann Prankl, Martin Antenreiter, Peter Auer, and Markus Vincze. Consistent interpretation of image sequences to improve object models on the fly. In Justus H. Piater Mario Fritz, Bernt Schiele, editor, Proceedings of the 7th International Conference on Computer Vision Systems: Computer Vision System, number 5815 in Lecture Notes In Computer Science, pages 384 – 393. Springer, 2009.

[9]

Peter Auer, Harald Burgsteiner, and Wolfgang Maass. A learning rule for very simple universal approximators consisting of a single layer of perceptrons. Neural networks, 21 5:786 – 795, 2008.

[10]

Alex Po Leung and Peter Auer. An efficient search algorithm for content-based image retrieval with user feedback. In Workshop on Video Mining at IEEE International Conference on Data Mining (ICDM), Pisa, Italy, 2008.

[11]

Peter Auer and Ronald Ortner. Logarithmic online regret bounds for undiscounted reinforcement learning. In J. Platt B. Schölkopf and T. Hoffman, editors, Advances in Neural Information Processing Systems 19, pages 49 – 56, Cambridge, MA, 2007. MIT Press.

[12]

Peter Auer and Ronald Ortner. A new pac bound for intersection-closed concept classes. Machine learning, 66 2-3:151 – 163, 2007.

[13]

Peter Auer, Ronald Ortner, and Csaba Szepesvári. Improved rates for the stochastic continuum-armed bandit problem. In Claudio Gentile Nader Bshouty, editor, Proceedings of the 20th Annual Conference on Learning Theory, Lecture Notes in Artificial Intelligence, pages 454 – 468. Springer, 2007.

[14]

C. Allenberg, Peter Auer, L. Györfi, and G. Ottucsák. Hannan consistency in online learning in case of unbounded losses under partial monitoring. In Algorithmic Learning Theory, pages 229 – 243, Berlin [u.a.], 2006. Springer.

[15]

Martin Antenreiter and Peter Auer. A reasoning system to track movements of totally occluded objects. In International Cognitive Vision Workshop (ICVW), Workshop Proceedings at ECCV 2006 (electronic), Graz, Austria, 2006.

[16]

Martin Antenreiter, Christian Savu-Krohn, and Peter Auer. Visual classification of images by learning geometric appearances through boosting. In Simone Marinai Friedhelm Schwenker, editor, IAPR Workshop, ANNPR, Lecture Notes in Computer Science, pages 233 – 243, Berlin / Heidelberg, 2006. Springer. (PDF)

[17]

P. Auer. Exploration vs. exploitation challange framework. In Second Pascal Challenge Workshop, 2006.

[18]

Peter Auer. Generic object recognition with boosting. IEEE Transactions on Pattern Analysis and Machine Intelligence Pattern analysis and machine intelligence : PAMI, 28 3:416 – 431, 2006.

[19]

Peter Auer and Nicoló Cesa-Bianchi. A distributed voting scheme to maximize preferences. Theoretical Informatics and Applications, pages 389 – 403, 2006.

[20]

Peter Auer, Thomas Jaksch, and Ronald Ortner. Empirical evaluation of a new online reinforcement learning algorithm. technical report, 2006. University of Leoben, Chair of Information Technology, Technical Report CIT-2006-01.

[21]

Christian Savu-Krohn and Peter Auer. A simple feature extraction for high dimensional image representations. In S. Gunn J. Shawe-Taylor C. Saunders, M. Grobelnik, editor, Subspace, Latent Structure and Feature Selection, Lecture Notes in Computer Science, pages 163 – 172. Springer, 2006.

[22]

P. Auer. Competitive reinforcement learning. In Models of Behavioural Learning Workshop (at NIPS 2005) Canada, 2005.

[23]

P. Auer. Models for trading exploration and exploitation using upper confidence bounds. In EU Pascal Workshop on Principled methods of trading exploration and exploitation. London UK am 6.7.06, 2005.

[24]

Peter Auer and Martin Antenreiter. Object recognition using geometric properties and a variant of boosting. In Michael Zillich Markus Vincze, editor, 1st Austrian Cognitive Vision Workshop, 2005, pages 43 – 50, Wien, 2005. ÖCG-Schriftenreihe 186. (PDF)

[25]

Peter Auer and Ronald Ortner. A boosting approach to multiple-instance learning. technical report, 2005. University of Leoben, Chair of Information Technology, Technical Report CIT-2005-01.

[26]

Peter Auer and Ronald Ortner. Online regret bounds for a new reinforcement learning algorithm. In Michael Zillich Markus Vincze, editor, 1st Austrian Cognitive Vision Workshop, ÖCG Schriftenreihe, pages 35 – 42, Wien, 2005. Austrian Computer Society (ÖCG).

[27]

Christian Savu-Krohn and Peter Auer. A simple feature extraction for high dimensional image representations (preliminary version). In Michael Zillich Markus Vincze, editor, 1st Austrian Cognitive Vision Workshop, ÖCG Schriftenreihe, pages 27 – 32, Wien, 2005. Austrian Computer Society (ÖCG).

[28]

Peter Auer and Ronald Ortner. A boosting approach to multiple instance learning. In Jean Francois Boulicaut et al., editor, Machine Learning, 15th European Conference on Machine Learning, ECML 2004, Lecture Notes in Artificial Intelligence, pages 63 – 74. Springer, 2004. (PDF)

[29]

Peter Auer and Ronald Ortner. A new pac-bound for intersection-closed concept classes. In Yoram Singer John Shawe-Taylor, editor, Learning Theory, 17th Annual Conference on Learning Theory, Lecture Notes in Computer Science, pages 408 – 414. Springer, 2004. (PDF)

[30]

Peter Auer, A. Opelt, M. Fussenegger, and A. Pinz. Generic object recognition with boosting. technical report, 2004. EMT, TU Graz, Austria 2004, Technical Report TR-EMT-2004-01.

[31]

M. Fussenegger, A. Opelt, A. Pinz, and Peter Auer. Object recognition using segmentation for feature detection. In J. Scharinger W. Burger, editor, Digital Imaging in Media and Education, Proc. of the 28th OEAGM/AAPR Conference; OCG 2004 (179 Schriftenreihe), pages 103 – 110, 2004.

[32]

M. Fussenegger, A. Opelt, A. Pinz, and Peter Auer. Object recognition using segmentation for feature detection. In 17th International Conference on Pattern Recognition (ICPR 2004), pages 41 – 44, 2004.

[33]

A. Opelt, M. Fussenegger, A. Pinz, and Peter Auer. Weak hypotheses and boosting for generic object detection and recognition. In J. Matas T. Pajdla, editor, Computer Vision - ECCV 2004, 8th European Conference on Computer Vision, Lecture Notes in Computer Science, pages 71 – 84. Springer, 2004.

[34]

Peter Auer. Using confidence bounds for exploitation-exploration trade-offs. Journal of machine learning research, pages 397 – 422, 2002.

[35]

Peter Auer, H. Burgsteiner, and Wolfgang 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, Lecture Notes in Computer Science, pages 123 – 128. Springer, 2002.

[36]

Peter Auer, N. Cesa-Bianchi, and P. Fischer. Finite time analysis of the multiarmed bandit problem. Machine learning, 47 2/3:235 – 256, 2002.

[37]

Peter Auer, Nicoló Cesa-Bianchi, N. Freund, and R. E. Schapire. The nonstochastic multiarmed bandit problem. SIAM Journal on Computing, 32 (1):48 – 77, 2002.

[38]

Peter Auer, Nicoló Cesa-Bianchi, and C. Gentile. Adaptive and self-confident online learning algorithms. Journal of computer and system sciences (JCSS), 64 1:48 – 78, 2002.

[39]

P. Auer, N. Cesa-Bianchi, and C. Gentile. Adaptive and self-confident on-line learning algorithms. Journal version, 2001.

[40]

Peter Auer. An improved on-line algorithm for learning linear evaluation functions. In Proceedings of the Thirteenth Annual Conference on Computational Learning Theory (COLT 2000), pages 118 – 125. Morgan Kaufmann, 2000.

[41]

Peter Auer. Using upper confidence bounds for online learning. In 41th Annual Symposium on Foundations of Computer Science, pages 270 – 293. IEEE Computer Society, 2000.

[42]

Peter Auer and C. Gentile. Adaptive and self-confident on-line learning algorithms. In Proceedings of the Thirteenth Annual Conference on Computational Learning Theory (COLT 2000), pages 107 – 117. Morgan Kaufmann, 2000.

[43]

Peter Auer and P. M. Long. Structural results about on-line learning models with and without queries. Machine learning, 36:147 – 181, 1999.

[44]

Peter Auer, N. Cesa-Bianchi, and P. Fischer. Finite time analysis of the multiarmed bandit problem. In IT Workshop on Decision, Estimation, Classification and Imaging, 1999.

[45]

P. Auer. Learning decision trees from multiple instances. In preparation, 1998.

[46]

P. Auer. On the local time of a Wiener process in R². In preparation, 1998.

[47]

Peter Auer. On learning from ambiguous information. Periodica polytechnica / Electrical engineering, 1 42:115 – 122, 1998.

[48]

Peter Auer. Some thoughts on boosting and neural networks. In H. Koch L. Cromme, T. Kolb, editor, 3. Cottbuser Workshop "Aspekte des Neuronalen Lernens", pages 11 – 28. Shaker Verlag, 1998. 3. Cottbuser Workshop "Aspekte des Neuronalen Lernens".

[49]

Peter Auer and Nicoló Cesa-Bianchi. On-line learning with malicious noise and the closure algorithm. Annals of mathematics and artificial intelligence, 23:83 – 99, 1998.

[50]

Peter Auer and W. Maass. Introduction to the special issue on computational learning theory. Algorithmica, 22 1/2:1 – 2, 1998.

[51]

Peter Auer and M. K. Warmuth. Tracking the best disjunction. Machine learning, 32:127 – 150, 1998.

[52]

Peter Auer, P. M. Long, and A. Srinivasan. Approximating hyper-rechtangles: Learning and pseudorandom sets. Journal of computer and system sciences (JCSS), 57 3:376 – 388, 1998.

[53]

P. Auer. Boosting real valued hypotheses. Manuscript, 1997.

[54]

P. Auer. Selecting optimal attributes for clustering. Manuscript, 1997.

[55]

Peter Auer. Learning nested differences in the presence of malicious noise. Theoretical Computer Science, 185:159 – 175, 1997. Theoretical Computer Science.

[56]

Peter Auer. On learning from multi-instance examples: Empirical evaluation of a theoretical approach. pages 21 – 29. Morgan Kaufmann, 1997. 14th Int. Conference Machine Learning.

[57]

Peter Auer, J. Kivinen, and M. K. Warmuth. The perceptron algorithm vs. winnow: linear vs. logarithmic mistake bounds when few input variables are relevant. Artificial intelligence, pages 325 – 343, 1997.

[58]

Peter 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 Press, 1997.

[59]

Peter Auer and K. Hornik. Limit laws for the maximal and minimal increments of the poisson process. Studia Scientiarum Mathematicarum Hungarica, 31:1 – 13, 1996.

[60]

Peter Auer and K. Hornik. The number of points of an empirical or (poisson) process covered by unions of sets. Journal of multivariate analysis (JMVAAI), pages 37 – 51, 1996.

[61]

Peter Auer, P. Caianiello, and N. Cesa-Bianchi. Tight bounds on the cumulative profit of distributed voters. In Proc. of the 15th Annual ACM Symposium on Principles of Distributed Computing, pages 312 – 312, 1996.

[62]

Peter Auer, M. Herbster, and M. K. Warmuth. Exponentially many local minima for single neurons. In M. E. Hasselmo D. S. Touretzky, M. C. Mozer, editor, Advances in Neural Information Processing System 8, pages 316 – 322. MIT Press, 1996.

[63]

Peter Auer, S. Kwek, Wolfgang Maass, and M. K. Warmuth. Learning of depth two neurals nets with constant fan-in at the hidden nodes. In Proc. of the Ninth Annual ACM Conference on Computational Learning Theory, pages 333 – 343. ACM Press, 1996.

[64]

Peter Auer. Learning nested differences in the presence of malicious noise. In Thomas Zeugmann Klaus P. Jantke, Takeshi Shinohara, editor, 6th International Workshop, ALT 95, pages 123 – 137, 1995.

[65]

Peter Auer and M. K. Warmuth. Tracking the best disjunction. In Proc. of the 36th Annual Sympsoium on Foundations of Computer Science, pages 312 – 321. IEEE Computer Society Press, 1995.

[66]

Peter Auer, Nicoló Cesa-Bianchi, Y. Freund, and R. E. Schapire. Gambling in a rigged casino: The adversarial multi-armed bandit problem. In 36th Annual Symposium on Foundations of Computer Science, pages 322 – 331. IEEE Computer Science Press, Los Alamitos, CA, 1995.

[67]

Peter Auer, R. C. Holte, and W. Maass. Theory and applications of agnostic (pac)-learning with small decision trees. In S. Russel A. Priedities, editor, Proc. of the 12th International Machine Learning Conference, pages 21 – 29. Morgan Kaufmann, 1995.

[68]

Peter Auer, P. M. Long, W. Maass, and G. J. Wöginger. On the complexity of function learning. Machine learning, 18:187 – 230, 1995.

[69]

Peter Auer and Nicoló Cesa-Bianchi. On-line learning with malicious noise and the closure algorithm. In Klaus P. Jantke Setsuo Arikawa, editor, Algorithmic Learning Theory, 4th International Workshop on Analogical and Inductive Inference, AII '94, 5th International Workshop on Algorithmic Learning Theory, ALT '94, Lecture Notes in Artificial Intelligence, pages 229 – 247. Springer, 1994.

[70]

Peter Auer and K. Hornik. On the number of points of a homogeneous poisson process. Journal of multivariate analysis (JMVAAI), 1:115 – 156, 1994.

[71]

Peter Auer and P. M. Long. Simulating access to hidden information while learning. In Proc. of the 26th Annual ACM Symposium on the Theory of Computing, pages 263 – 272. ACM Press, 1994.

[72]

Peter Auer, K. Hornik, H. Stinchombe, and H. White. Degree of approximation results for feedforward networks approximating unknown mappings and their derivatives. Neural computation, 6:1262 – 1275, 1994.

[73]

Peter Auer. On-line learning of rectangles in noisy environments. In Sixth Annual ACM Conference on Computational Learning Theory (COLT 1993), pages 253 – 261. ACM Press, New York, NY, 1993.

[74]

Peter Auer, P. M. Long, Wolfgang Maass, and Gerhard J. Wöginger. On the complexity of function learning. In Sixth Annual ACM Conference on Computational Learning Theory (COLT 1993), pages 392 – 401. ACM Press, 1993.

[75]

Peter Auer. Solving string equations with constant restrictions. pages 103 – 132. Springer, 1991.

[76]

Peter Auer. Unification in the combination of disjoint theories. pages 177 – 186. Springer, 1991.

[77]

Peter Auer, K. Hornik, and P. Revesz. Some limit theorems for the homogeneous poisson process. Statistics and probability letters, 12:91 – 96, 1991.

[78]

Peter Auer. The circle homogeneously covered by random walk on z². Statistics and probability letters, 9:403 – 407, 1990.

[79]

P. Auer and K. Hornik. On the multivariate spacings of Poisson and empirical processes. Manuscript.