Strategies for Prediction Under Imperfect Monitoring

References

• Auer P., Cesa-Bianchi N., Gentile C. Adaptive and self-confident on-line learning algorithms. J. Comput. System Sci. (2002) 64:48–75Crossref, Google Scholar
• Auer P., Cesa-Bianchi N., Freund Y., Schapire R. The nonstochastic multiarmed bandit problem. SIAM J. Comput. (2002) 32:48–77Crossref, Google Scholar
• Azuma K. Weighted sums of certain dependent random variables. Tohoku Math. J. (1967) 68:357–367Crossref, Google Scholar
• Baños A. On pseudo-games. Ann. Math. Statist. (1968) 39:1932–1945Crossref, Google Scholar
• Bertsekas D. P.Nonlinear Programming (1995) (Athena Scientific, Belmont, MA) Google Scholar
• Blackwell D. Controlled random walks. Proc. Internat. Congress of Mathematicians, 1954 (1956) III(North-Holland, Amsterdam) 336–338Google Scholar
• Cesa-Bianchi N. Analysis of two gradient-based algorithms for on-line regression. J. Comput. System Sci. (1999) 59(3):392–411Crossref, Google Scholar
• Cesa-Bianchi N., Lugosi G. On prediction of individual sequences. Ann. Statist. (1999) 27:1865–1895Crossref, Google Scholar
• Cesa-Bianchi N., Lugosi G.Prediction, Learning, and Games (2006) (Cambridge University Press, New York) Crossref, Google Scholar
• Cesa-Bianchi N., Lugosi G., Stoltz G. Regret minimization under partial monitoring. Math. Oper. Res. (2006) 31:562–580Link, Google Scholar
• Cesa-Bianchi N., Mansour Y., Stoltz G. Improved second-order bounds in prediction with expert advice. Machine Learning (2007) 66:321–352Crossref, Google Scholar
• Cesa-Bianchi N., Freund Y., Haussler D., Helmbold D. P., Schapire R., Warmuth M. How to use expert advice. J. ACM (1997) 44(3):427–485Crossref, Google Scholar
• Chen X., White H. Laws of large numbers for Hilbert space-valued mixingales with applications. Econometric Theory (1996) 12(2):284–304Crossref, Google Scholar
• Foster D., Vohra R. Asymptotic calibration. Biometrika (1998) 85:379–390Crossref, Google Scholar
• Freedman D. A. On tail probabilities for martingales. Ann. Probab. (1975) 3:100–118Crossref, Google Scholar
• Hannan J. Approximation to Bayes risk in repeated play. Contributions Theory Games (1957) 3:97–139Google Scholar
• Hart S., Mas-Colell A. A simple adaptive procedure leading to correlated equilibrium. Econometrica (2000) 68:1127–1150Crossref, Google Scholar
• Hart S., Mas-Colell A. A reinforcement procedure leading to correlated equilibrium. Economic Essays: A Festschrift for Werner Hildenbrand (2002) (Springer, New York) 181–200Google Scholar
• Hoeffding W. Probability inequalities for sums of bounded random variables. J. Amer. Statist. Assoc. (1963) 58:13–30Crossref, Google Scholar
• Kivinen J., Warmuth M. Exponentiated gradient versus gradient descent for linear predictors. Inform. Comput. (1997) 132(1):1–63Crossref, Google Scholar
• Littlestone N., Warmuth M. The weighted majority algorithm. Inform. Comput. (1994) 108:212–261Crossref, Google Scholar
• Mannor S., Shimkin N. On-line learning with imperfect monitoring. Proc. 16th Annual Conf. Learn. Theory (2003) (Springer, New York) 552–567Crossref, Google Scholar
• Megiddo N. On repeated games with incomplete information played by non-Bayesian players. Internat. J. Game Theory (1980) 9:157–167Crossref, Google Scholar
• Mertens J.-F., Sorin S., Zamir S. Repeated games. (1994) . CORE discussion paper 9420, 9421, 9422, Université catholique de Louvain (UCL), Louvain-la-Neuve, BelgiumGoogle Scholar
• Piccolboni A., Schindelhauer C. Discrete prediction games with arbitrary feedback and loss. Proc. 14th Annual Conf. Computational Learn. Theory (2001) (Springer, New York) 208–223Crossref, Google Scholar
• Rustichini A. Minimizing regret: The general case. Games Econom. Behav. (1999) 29:224–243Crossref, Google Scholar
• Vovk V. Aggregating strategies. Proc. 3rd Annual Workshop on Computational Learn. Theory (1990) (Morgan Kaufmann Publishers Inc., San Francisco) 372–383Crossref, Google Scholar
• Vovk V. A game of prediction with expert advice. J. Comput. System Sci. (1998) 56(2):153–173Crossref, Google Scholar
• Weissman T., Merhav N. Universal prediction of binary individual sequences in the presence of noise. IEEE Trans. Inform. Theory (2001) 47:2151–2173Crossref, Google Scholar
• Weissman T., Merhav N., Somekh-Baruch A. Twofold universal prediction schemes for achieving the finite state predictability of a noisy individual binary sequence. IEEE Trans. Inform. Theory (2001) 47:1849–1866Crossref, Google Scholar