Dr Alexey Chernov

Dept Computer Science
Royal Holloway, University of London
Egham, Surrey, TW20 0EX, United Kingdom

Email: chernov@cs.rhul.ac.uk



I moved, and now I am a lecturer in statistics at the University of Brighton, but you can still contact me via the address above as I remain an honorary fellow of Computer Learning Research Centre.

I was a postdoctoral researcher in the Department of Computer Science at Royal Holloway, University of London in 2007-2011. I worked with Volodya Vovk on EPSRC project Practical Competitive Prediction.

My main research interests are sequential online learning (including prediction with expert advice, kernel methods, universal inductive inference) and topological methods in pattern recognition. I am also interested in Kolmogorov complexity and algorithmic foundations for probability theory, reinforcement learning, and learning in the limit.

I obtained PhD in mathematics in 2003 from Moscow State University (Department of Mathematical Logic and Theory of Algorithms). My thesis is on semantics for propositional logic with the help of Kolmogorov complexity, supervisor prof. Vereshchagin. Then I worked with Jürgen Schmidhuber in IDSIA (Lugano, Switzerland) and with Alexander Shen in LIF (Marseilles, France). In 2011-2012, I was a postdoc in the Department of Mathematical Sciences at Durham University. In 2012-2014, I was a lecturer in Mathematics at the University of Bedfordshire. See also my CLRC page, my old IDSIA page.

Publications:

(see also Google Scholar page)
  1. Dmitry Adamskiy, Wouter M. Koolen, Alexey Chernov, and Vladimir Vovk. A closer look at adaptive regret. Journal of Machine Learning Research, 17(23):1-21, 2016. JMLR link.
    Conference version: Proc. of ALT 2012, LNAI 7568, pp. 290-304.

  2. Yuri Kalnishkan, Dmitry Adamskiy, Alexey Chernov and Tim Scarfe. Specialist experts for prediction with side information. Data Mining Workshop (ICDMW), 2015 IEEE International Conference on. IEEE, pp. 1470-1477. IEEE link.

  3. Alexey Chernov and Vitaliy Kurlin. Reconstructing persistent graph structures from noisy images. DGCI 2013 Demo Session 7th IAPR International Conference on Discrete Geometry for Computer Imagery, Imagen-A, 2013, vol. 3, n. 5, pp. 19-22. Imagen-A link.

  4. Alexey Chernov, Fedor Zhdanov. Prediction with Expert Advice under Discounted Loss. Proc. of ALT 2010, LNCS 6331, pp. 255-269. arXiv.

  5. Alexey Chernov, Vladimir Vovk. Prediction with Advice of Unknown Number of Experts. Proceedings of the Twenty-Sixth Conference on Uncertainty in Artificial Intelligence (UAI-2010), AUAI Press, pp. 117-125. Preliminary online proceedings, arXiv.

  6. Alexey Chernov, Yuri Kalnishkan, Fedor Zhdanov, Vladimir Vovk. Supermartingales in Prediction with Expert Advice. Theoretical Computer Science, 2010, vol. 411(29-30), pp. 2647-2669. ScienceDirect link, arXiv.
    Conference version: Proc. of ALT 2008, LNCS 5254, pp. 199-213. Springer link.

  7. Alexey Chernov, Vladimir Vovk. Prediction with Expert Evaluators' Advice. Proc. of ALT 2009, LNCS 5809, pp. 8-22. Springer link, arXiv.

  8. Alexey Chernov, Alexander Shen, Nikolai Vereshchagin, Vladimir Vovk. On-Line Probability, Complexity and Randomness. Proc. of ALT 2008, LNCS 5254, pp. 138-153. Springer link.

  9. Alexey Chernov, Marcus Hutter, Juergen Schmidhuber. Algorithmic complexity bounds on future prediction errors. Information and Computation, 2007, 205-2, pp. 242-261. ScienceDirect link, arXiv.
    Alexey Chernov, Marcus Hutter, Juergen Schmidhuber. Complexity Monotone in Conditions and Future Prediction Errors. Dagstuhl Seminar Proceedings 06051, 2006. pdf
    Alexey Chernov, Marcus Hutter. Monotone Conditional Complexity Bounds on Future Prediction Errors. Proc. of 16th International Conf. on Algorithmic Learning Theory (ALT-2005), LNCS 3734, pp. 414-428. Springer link Tech Report: IDSIA-16-05 pdf, arXiv.
    Alexey Chernov, Juergen Schmidhuber. On decrease of a priori randomness deficiency. Tech Report IDSIA-12-05, IDSIA, Manno(Lugano), Switzerland, 2005. pdf

  10. Alexey Chernov, Juergen Schmidhuber. Prefix-like Complexities and Computability in the Limit. Proc. of Second Conference on Computability in Europe CiE 2006, LNCS 3988, pp. 85-93. Springer link
    Alexey Chernov, Juergen Schmidhuber. Prefix-like Complexities of Finite and Infinite Sequences on Generalized Turing Machines. Tech Report IDSIA-11-05, IDSIA, Manno(Lugano), Switzerland, 2005. pdf

  11. A.Chernov. Finite Problems and the Logic of the Weak Law of Excluded Middle. Matematicheskie Zametki, 2005, vol. 77, no. 2, pp. 291-302, in Russian (ps.gz). English translation: Mathematical Notes, 2005, vol. 77, no. 1, pp. 263-272. Springer link
    Preliminary version: Dep. in VINITI 3.07.2003 No.1263-B2003, in Russian (ps.gz).

  12. A.Chernov. Complexity of Sets Obtained as Values of Propositional Formulas. Matematicheskie Zametki, 2004, vol. 75, no. 1, pp. 142-150, in Russian (ps.gz). English translation: Mathematical Notes, 2004, vol. 75, no. 1, pp. 131-139. Springer link

  13. A.Chernov, D.Skvortsov, E.Skvortsova, N.Vereshchagin. Variants of Realizability for Propositional Formulas and the Logic of the Weak Law of Excluded Middle. Mathematical Logic and Algebra. Proceedings of Steklov Mathematical Insitute, 2003, vol. 242, pp. 77-97.
    Conference version: Computer Science Logic 16th International Workshop CSL 2002, LNCS 2471, pp. 74-88. Springer link

  14. A.Chernov, An.Muchnik, A.Romashchenko, A.Shen, N.Vereshchagin. Upper semi-lattice of binary strings with the relation 'x is simple conditional to y'. Theoretical Computer Science, 2002, v.271, pp. 69-95. ScienceDirect

Unpublished technical reports

Fedor Zhdanov, Alexey Chernov, Yuri Kalnishkan. Aggregating Algorithm competing with Banach lattices. arXiv

Alexey Chernov, Juergen Schmidhuber. Asymmetric Planning for Incremental Real-Time Heuristic Search. Tech Report IDSIA-15-06. pdf

PhD thesis, in Russian

On Some Variants of the Notion of Realizability. Moscow State University, 2003. pdf, summary in Russian ps

Some talk slides

Multiobjective prediction with expert advice, Royal Holloway, June 2010.
Prediction with expert advice and game-theoretic supermartingales, Durham, March 2010.
Practical aspects of Levin's neutral measure, Marseilles, July 2009.
Complexity monotone in conditions and future prediction errors, Dagstuhl Seminar 06051, 2006.
Kolmogorov complexity and logical formulas, Turing Days'06, Istanbul, 27 May 2006. (Invited lecture partially based on my PhD thesis)