Vladimir Vovk's publications

Vladimir Vovk's selected publications

(some of them are available elsewhere on this web site)

PhD Thesis

Predictability of algorithmically random sequences, Moscow State University, June 1988. PhD Advisors Academician Andrei Kolmogorov and Professor Aleksei Semenov.

Books

Probability and finance: it's only a game (with Glenn Shafer), New York: Wiley, 2001. Japanese translation: Tokyo: Iwanami Shoten, 2006.
Algorithmic learning in a random world (with Alex Gammerman and Glenn Shafer), New York: Springer, 2005.

Journal Publications

On the concept of the Bernoulli property. Russian Mathematical Surveys 41, 247–248 (1986).
On a randomness criterion. Soviet Mathematics Doklady 35, 656–660 (1987). Another English translation
The law of the iterated logarithm for random Kolmogorov, or chaotic, sequences. Theory of Probability and Applications 32, 413–425 (1987).
Kolmogorov–Stout law of the iterated logarithm. Mathematical Notes 44, 502–507 (1988).
Prediction of stochastic sequences. Problems of Information Transmission 25, 285–296 (1989).
Asymptotic efficiency of estimators: an algorithmic approach. Theory of Probability and Applications 36, 329–343 (1991).
Universal forecasting algorithms. Information and Computation 96, 245–277 (1992).
On the empirical validity of the Bayesian method (joint work with Vladimir V V'yugin). Journal of the Royal Statistical Society B 55, 253–266 (1993).
A logic of probability, with application to the foundations of statistics (with discussion). Journal of the Royal Statistical Society B 55, 317–351 (1993).
Forecasting point and continuous processes: prequential analysis. Test 2, 189–217 (1993).
Prequential level of impossibility with some applications (joint work with Vladimir V V'yugin). Journal of the Royal Statistical Society B 56, 115–123 (1994).
A strictly martingale version of Kolmogorov's strong law of large numbers. Theory of Probability and Applications 41, no 3 (1996).
Learning about the parameter of the Bernoulli model. Journal of Computer and System Sciences 55, 96–104 (1997).
A game of prediction with expert advice. Journal of Computer and System Sciences 56, 153–173 (1998).
Derandomizing stochastic prediction strategies. Machine Learning 35, 247–282 (1999).
Editorial—Kolmogorov complexity (joint work with Alex Gammerman). Computer Journal 42, 251 (1999).
Kolmogorov complexity: sources, theory and applications (joint work with Alex Gammerman). Computer Journal 42, 252–255 (1999).
Complexity Approximation Principle (joint work with Alex Gammerman). Computer Journal 42, 318–322 (1999).
Prequential probability: principles and properties (joint work with A Philip Dawid). Bernoulli 5, 125–162 (1999).
Probability theory for the Brier game. Theoretical Computer Science 261, 57–79 (2001).
Predicting nearly as well as the best pruning of a decision tree through dynamic programming scheme (joint work with Eiji Takimoto and Akira Maruoka). Theoretical Computer Science 261, 179–209 (2001).
Competitive on-line statistics. International Statistical Review 69, 213–248 (2001).
Kolmogorov's contributions to the foundations of probability. Problems of Information Transmission 39, 21–31 (2003).
Loss functions, complexities and the Legendre transformation (joint work with Yuri Kalnishkan and Misha Vyugin). Theoretical Computer Science 313, 195–207 (2004).
Universal well-calibrated algorithm for on-line classification. Journal of Machine Learning Research, 5, 575–604 (2004).
How many strings are easy to predict? (joint work with Yuri Kalnishkan and Misha Vyugin). Information and Computation, 201, 55–71 (2005). Conference version: COLT 2003.
Good randomized sequential probability forecasting is always possible (joint work with Glenn Shafer). Journal of the Royal Statistical Society B 67, 747–763 (2005).
Well-calibrated predictions from on-line compression models. Theoretical Computer Science (Special Issue devoted to ALT 2003) 364, 10–26 (2006).
Criterion of calibration for Transductive Confidence Machine with limited feedback (joint work with Ilia Nouretdinov). Theoretical Computer Science (Special Issue devoted to ALT 2003) 364, 3–9 (2006).
The sources of Kolmogorov's Grundbegriffe (joint work with Glenn Shafer). Statistical Science 21, 70–98 (2006).
Hedging predictions in machine learning (the second Computer Journal lecture, with discussion, joint work with Alex Gammerman). Computer Journal 50, 151–177 (2007).
Non-asymptotic calibration and resolution. Theoretical Computer Science (Special Issue devoted to ALT 2005) 387, 77–89 (2007).
Competing with wild prediction rules. Machine Learning (Special Issue devoted to COLT 2006) 69, 193–212 (2007).
A tutorial on conformal prediction. Journal of Machine Learning Research 9, 371–421 (2007).
Leading strategies in competitive on-line learning. Theoretical Computer Science (Special Issue devoted to ALT 2006), accepted for publication.
The game-theoretic capital asset pricing model. International Journal of Approximate Reasoning, accepted for publication.
Merging of opinions in game-theoretic probability. Annals of the Institute of Statistical Mathematics, accepted for publication.

Conferences

Aggregating strategies. In: Proceedings of the 3rd Annual Workshop on Computational Learning Theory (ed by M Fulk and J Case), pp 371–383. San Mateo, CA: Morgan Kaufmann, 1990.
An optimal-control application of two paradigms of on-line learning. In: Proceedings of the 7th Annual Workshop on Computational Learning Theory (ed by M K Warmuth), pp 98–109. New York: ACM Press, 1994.
Minimum description length estimators under the optimal coding scheme. In: Computational learning theory (ed by P Vitanyi), Lecture Notes in Computer Science, vol 904, pp 237–251. Berlin: Springer, 1995.
Learning an optimal decision strategy in an influence diagram with latent variables. In: Proceedings of the 9th Annual Conference on Computational Learning Theory, pp 110–121. 1996.
Universal portfolio selection (joint work with Chris Watkins). In: Proceedings of the 11th Annual Conference on Computational Learning Theory, pp 12–23. 1998.
Learning by transduction (joint work with Alex Gammerman and Vladimir Vapnik). In: Proceedings of the 14th Conference on Uncertainty in Artificial Intelligence, pp 148–156. San Francisco, CA: Morgan Kaufmann, 1998.
Ridge Regression learning algorithm in dual variables (joint work with Craig Saunders and Alex Gammerman). In: Proceedings of the 15th International Conference on Machine Learning (ed by J W Shavlik), pp 515–521. San Francisco, CA: Morgan Kaufmann, 1998.
Machine-learning applications of algorithmic randomness (joint work with Craig Saunders and Alex Gammerman). In: Proceedings of the 16th International Conference on Machine Learning, p 444–453. 1999.
Transduction with confidence and credibility (joint work with Craig Saunders and Alex Gammerman). In: Proceedings of the 16th International Joint Conference on Artificial Intelligence, pp 722–726. 1999.
Ridge Regression Confidence Machine (joint work with Ilia Nouretdinov and Tom Melluish). In: Proceedings of the 18th International Conference on Machine Learning, 2001.
Pattern recognition and density estimation under the general iid assumption (joint work with Ilia Nouretdinov, Michael Vyugin and Alex Gammerman). In: Proceedings of the 14th Annual Conference on Computational Learning Theory and 5th European Conference on Computational Learning Theory (ed by D Helmbold and B Williamson), Lecture Notes in Artificial Intelligence, vol 2111, pp 337–353. 2001.
Comparing the Bayes and typicalness frameworks (joint work with Tom Melluish, Craig Saunders and Ilia Nouretdinov). In: Machine Learning: ECML 2001. Proceedings of the 12th European Conference on Machine Learning (ed by L De Raedt and P Flash), Lecture Notes in Artificial Intelligence, vol 2167, pp 360–371. 2001.
On-line confidence machines are well-calibrated. In: Proceedings of the 43rd Annual Symposium on Foundations of Computer Science, pp 187–196. Los Alamitos, CA: IEEE Computer Society, 2002.
Asymptotic optimality of Transductive Confidence Machine. In: Proceedings of the 13th International Conference on Algorithmic Learning Theory (ed by N Cesa-Bianchi, M Numao and R Reischuk), Lecture Notes in Artificial Intelligence, vol 2533, pp 336–350. 2002.
Universal well-calibrated algorithm for on-line classification. In: Learning Theory and Kernel Machines. Proceedings of the 16th Annual Conference on Learning Theory and Seventh Kernel Workshop, COLT/Kernel 2003 (ed by B Schölkopf and M K Warmuth), Lecture Notes in Artificial Intelligence, vol 2777, pp 358–372. Berlin: Springer, 2003.
Testing exchangeability on-line (joint work with Ilia Nouretdinov and Alex Gammerman). Proceedings of the 20th International Conference on Machine Learning (ed by T Fawcett and N Mishra), pp 768–775. Menlo Park, CA: AAAI Press, 2003.
On-line prediction with kernels and the Complexity Approximation Principle (joint work with Alex Gammerman and Yura Kalnishkan). In: Proceedings of the 20th Conference on Uncertainty in Artificial Intelligence (ed by M Chickering and J Halpern), pp 170–176. Arlington, VA: AUAI Press, 2004.
A criterion for the existence of predictive complexity for binary games (joint work with Yuri Kalnishkan and Misha Vyugin). In: Proceedings of the 15th International Conference on Algorithmic Learning Theory (ed by S Ben-David, J Case and A Maruoka), Lecture Notes in Artificial Intelligence, vol 3244, pp 249–263, Heidelberg: Springer, 2004. (Full version: Technical Report CLRC-TR-04-04, Computer Learning Research Centre, Royal Holloway, University of London.)
Self-calibrating probability forecasting (joint work with Glenn Shafer and Ilia Nouretdinov). In: Advances in Neural Information Processing Systems 16 (ed by S Thrun, L K Saul, B Schölkopf). Cambridge, MA: MIT Press, 2004.
Defensive forecasting (joint work with Akimichi Takemura and Glenn Shafer). In: Proceedings of the 10th International Workshop on Artificial Intelligence and Statistics (ed by R G Cowell and Z Ghahramani), pp 365–372. Society for Artificial Intelligence and Statistics, 2005. Available electronically at http://www.gatsby.ucl.ac.uk/aistats/.
Defensive prediction with expert advice. In: Proceedings of the 16th International Conference on Algorithmic Learning Theory (ed by S Jain, H U Simon and E Tomita), Lecture Notes in Computer Science, vol 3734, pp 444–458. Berlin: Springer, 2005.
Defensive forecasting for linear protocols (joint work with Ilia Nouretdinov, Akimichi Takemura and Glenn Shafer). In: Proceedings of the 16th International Conference on Algorithmic Learning Theory (ed by S Jain, H U Simon and E Tomita), Lecture Notes in Computer Science, vol 3734, pp 444–458. Berlin: Springer, 2005.
On-line regression competitive with reproducing kernel Hilbert spaces (extended abstract). In: Theory and Applications of Models of Computation. Proceedings of the Third Annual Conference on Computation and Logic (ed by J-Y Cai, S B Cooper and A Li), Lecture Notes in Computer Science, vol 3959, pp 452–463. Berlin: Springer, 2006.
Competing with stationary prediction strategies. In: Proceedings of the 20th Annual Conference on Learning Theory (ed by N Bshouty and C Gentile), Lecture Notes in Artificial Intelligence, vol 4539, pp 439–453. Berlin: Springer, 2007.
Generalized entropies and asymptotic complexities of languages (joint work with Yura Kalnishkan and Misha Vyugin). In: Proceedings of the 20th Annual Conference on Learning Theory (ed by N Bshouty and C Gentile), Lecture Notes in Artificial Intelligence, vol 4539, pp 293–307, Berlin: Springer, 2007.
Prediction with expert advice for the Brier game (joint work with Fedor Zhdanov). In: Proceedings of the 25th International Conference on Machine Learning, 2008, accepted for publication.
For other publications, see my co-authors' web sites (Alex Gammerman, Harris Papadopoulos, Kostas Proedrou, David Sourkov,...).

Book Chapters

Another semantics for Pearl's action calculus. In: Computational Learning and Probabilistic Reasoning (ed by A Gammerman), pp 127–146 (Chapter 7). New York: Wiley, 1995.
Kolmogorov's complexity conception of probability. In: Statistics—Philosophy, Recent History and Relations to Science (ed by V F Hendricks, S A Pedersen, and K F Jørgensen), pp 51–69. Dordrecht: Kluwer, 2001.

Technical Reports

Finitary prequential probability: asymptotic results. Institute of New Technologies, Moscow, May 1991.
On-line learning in a finite-state environment: decision theoretic approach. Independent University of Moscow, Technical Report V-93-1, December 1993.
See also arXiv technical reports.

Last modified on 8 April 2008