Efficient tracking of large classes of experts

IEEE Transactions on Information Theory

Volumn 58, Issue 11, 2012, Pages 6709-6725

  Gyorgy, András ^a,b   Linder, Tamás ^c   Lugosi, Gábor ^d  

^a INSTITUTE OF EXPERIMENTAL MEDICINE   (Hungary)

^b UNIVERSITY OF ALBERTA   (Canada)

^c QUEEN S UNIVERSITY   (Canada)

^d UNIVERSITAT POMPEU FABRA   (Spain)

Author keywords

Algorithmic efficiency; changing environments; compound experts; data compression; individual sequences; nonstationary sources; sequential coding; sequential decision making; sequential prediction

Indexed keywords

CHANGING ENVIRONMENT; COMPOUND EXPERTS; INDIVIDUAL SEQUENCES; NON-STATIONARY SOURCES; SEQUENTIAL CODING; SEQUENTIAL DECISION MAKING; SEQUENTIAL PREDICTION;

ALGORITHMS; BINARY SEQUENCES; DATA COMPRESSION; OPTIMIZATION; TRACKING (POSITION);

FORECASTING;

EID: 84867973521     PISSN: 00189448     EISSN: None     Source Type: Journal    
DOI: 10.1109/TIT.2012.2209627     Document Type: Article

References (41)

1. N. Cesa-Bianchi and G. Lugosi, Prediction, Learning, and Games. Cambridge, U.K.: Cambridge Univ. Press, 2006.
2. F. M. J. Willems, "Coding for a binary independent piecewise-identically- distributed source," IEEE Trans. Inf. Theory, vol. 42, no. 6, pp. 2210-2217, Nov. 1996. (Pubitemid 126771547)
3. G. I. Shamir and N. Merhav, "Low-complexity sequential lossless coding for piecewise-stationary memoryless sources," IEEE Trans. Inf. Theory, vol. 45, no. 5, pp. 1498-1519, Jul. 1999.
4. M. Herbster and M. K. Warmuth, "Tracking the best expert," Mach. Learn., vol. 32, no. 2, pp. 151-178, 1998. (Pubitemid 40626079)
5. V. Vovk, "Derandomizing stochastic prediction strategies," Mach. Learn., vol. 35, no. 3, pp. 247-282, Jun. 1999.
6. W. Koolen and S. de Rooij, "Combining expert advice efficiently," in Proc. 21st Annu. Conf. Learn. Theory, Helsinki, Finland, Jul. 2008, pp. 275-286.
7. C. Monteleoni and T. S. Jaakkola, "Online learning of non-stationary sequences," in Advances in Neural Information Processing Systems, S. Thrun, L. Saul, and B. Schölkopf, Eds. Cambridge, MA: MIT Press, 2004, vol. 16.
8. S. de Rooij and T. van Erven, "Learning the switching rate by discretising Bernoulli sources online," in Proc. 12th Int. Conf. Artif. Intell. Statist., Clearwater Beach, FL, Apr. 2009, vol. 5, JMLRWorkshop and Conference Proceedings, pp. 432-439.
9. F. Willems and M. Krom, "Live-and-die coding for binary piecewise i.i.d. sources," in Proc. IEEE Int. Symp. Inf. Theory, Ulm, Germany, Jun.-Jul. 1997, p. 68.
10. A. György, T. Linder, and G. Lugosi, "Efficient tracking of the best of many experts," in Proc. Inf. Commun. Conf., Budapest, Hungary, Aug. 25-28, 2008, pp. 3-4.
11. E. Hazan and C. Seshadhri, "Efficient learning algorithms for changing environments," in Proc. 26th Annu. Int. Conf. Mach. Learn., 2009, pp. 393-400.
12. E. Hazan, A. Agarwal, and S. Kale, "Logarithmic regret algorithms for online convex optimization," Mach. Learn. J., vol. 69, no. 2-3, pp. 169-192, 2007. (Pubitemid 47574314)
13. R. E. Krichevsky and V. K. Trofimov, "The performance of universal encoding," IEEE Trans. Inf. Theory, vol. IT-27, no. 2, pp. 199-207, Mar. 1981.
14. Y. M. Shtarkov, "Universal sequential coding of single messages," Probl. Inf. Transmiss., vol. 23, pp. 3-17, 1987.
15. F.M. J.Willems, Y. N. Shtarkov, and T. J. Tjalkens, "The context-tree weighting method: Basic properties," IEEE Trans. Inf. Theory, vol. 41, no. 3, pp. 653-664, May 1995.
16. A. Kalai and S.Vempala, B. Schölkopf andM.Warmuth, Eds., "Efficient algorithms for the online decision problem," in Proc. 16th Annu. Conf. Learn. Theory 7th Kernel Workshop, New York, Aug. 2003, pp. 26-40. (Pubitemid 37053193)
17. E. Takimoto and M. K. Warmuth, "Path kernels and multiplicative updates," J. Mach. Learn. Res., vol. 4, pp. 773-818, 2003.
18. T. Linder and G. Lugosi, "A zero-delay sequential scheme for lossy coding of individual sequences," IEEE Trans. Inf. Theory, vol. 47, no. 6, pp. 2533-2538, Sep. 2001. (Pubitemid 32949900)
19. T. Weissman and N. Merhav, "On limited-delay lossy coding and filtering of individual sequences," IEEE Trans. Inf. Theory, vol. 48, no. 3, pp. 721-733, Mar. 2002. (Pubitemid 34239799)
20. A. György, T. Linder, and G. Lugosi, "Efficient algorithms and minimax bounds for zero-delay lossy source coding," IEEE Trans. Signal Process., vol. 52, no. 8, pp. 2337-2347, Aug. 2004.
21. S. Kozat and A. Singer, "Universal switching linear least squares prediction," IEEE Trans. Signal Process., vol. 56, no. 1, pp. 189-204, Jan. 2008.
22. S. Kozat and A. Singer, "Switching strategies for sequential decision problems with multiplicative loss with application to portfolios," IEEE Trans. Signal Process., vol. 57, no. 6, pp. 2192-2208, Jun. 2009.
23. S. Kozat and A. Singer, "Universal randomized switching," IEEE Trans. Signal Process., vol. 58, no. 3, pp. 1922-1927, Mar. 2010.
24. A. György, T. Linder, and G. Lugosi, "Tracking the best quantizer," IEEE Trans. Inf. Theory, vol. 54, no. 4, pp. 1604-1625, Apr. 2008. (Pubitemid 351512989)
25. M. Zinkevich, "Online convex programming and generalized infinitesimal gradient ascent," in Proc. 20th Int. Conf.Mach. Learn., Washington, DC, 2003, pp. 928-936.
26. M. Herbster and M. K. Warmuth, "Tracking the best linear predictor," J. Mach. Learn. Res., vol. 1, pp. 281-309, 2001. (Pubitemid 33687205)
27. G. Stoltz and G. Lugosi, "Internal regret in on-line portfolio selection," Mach. Learn., vol. 59, pp. 125-159, 2005. (Pubitemid 40890415)
28. A. Blum and Y. Mansour, "From external to internal regret," J. Mach. Learn. Res., vol. 8, pp. 1307-1324, Dec. 2007. (Pubitemid 47143711)
29. A. V. Chernov and F. Zhdanov, "Prediction with expert advice under discounted loss," in Algorithmic Learning Theory, 2010, pp. 255-269.
30. N. Merhav, "On the minimum description length principle for sources with piecewise constant parameters," IEEE Trans. Inf. Theory, vol. 39, no. 6, pp. 1962-1967, Nov. 1993.
31. E. Hazan and C. Seshadhri, Adaptive Algorithms for Online Decision Problems Electronic Colloquium on Computational Complexity, 2007, Tech. Rep. 07-088.
32. L. Lovász and S. Vempala, "Fast algorithms for logconcave functions: Sampling, rounding, integration and optimization," in Proc. 47th Annu. IEEE Symp. Found. Comput. Sci., 2006, pp. 57-68.
33. S. Bubeck, Introduction to Online Optimization Princeton University, NJ, 2011, Lecture Notes [Online]. Available: http://www.princeton.edu/~sbubeck/ BubeckLectureNotes.pdf
34. T. Cover and J. A. Thomas, Elements of Information Theory. New York: Wiley, 2006.
35. D. P. Helmbold and M. K. Warmuth, "Learning permutations with exponentialweights," J. Mach. Learn. Res., vol. 10, pp. 1705-1736, 2009.
36. W. M. Koolen, M. K. Warmuth, and J. Kivinen, "Hedging structured concepts," presented at the 23rd Annu. Conf. Learn. Theory, 2010.
37. N. Cesa-Bianchi and G. Lugosi, "Combinatorial bandits," J. Comput. Syst. Sci., vol. 78, pp. 1404-1422, 2012.
38. V. Dani, T. Hayes, and S. Kakade, "The price of bandit information for online optimization," presented at the Proc. Annu. Neural Information Processing Systems, 2008.
39. A. György, T. Linder, and G. Lugosi, "A follow the perturbed leadertype algorithm for zero-delay quantization of individual sequences," in Proc. Data Compress. Conf., Snowbird, UT, Mar. 2004, pp. 342-351.
40. S. Matloub and T. Weissman, "Universal zero delay joint sourcechannel coding," IEEE Trans. Inf. Theory, vol. 52, no. 12, pp. 5240-5250, Dec. 2006. (Pubitemid 46445371)
41. A. György and G. Neu, "Near-optimal rates for limited-delay universal lossy source coding," in Proc. IEEE Int. Symp. Inf. Theory, St. Petersburg, Russia, Jul.-Aug. 2011, pp. 2344-2348.