Supermartingales in prediction with expert advice

Chernov, Alexey; Kalnishkan, Yuri; Zhdanov, Fedor; Vovk, Vladimir

doi:10.1016/j.tcs.2010.04.003

Cited by 5 publications

(2 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper we will be discussing specialist experts as a special case of the theory of expert evaluators after [7], [8]. A simple extension of the AA may be used for specialist experts.…”

Section: Specialist Expertsmentioning

confidence: 99%

See 1 more Smart Citation

Specialist Experts for Prediction with Side Information

Kalnishkan

Adamskiy

Chernov

et al. 2015

2015 IEEE International Conference on Data Mining Workshop (ICDMW)

Self Cite

View full text Add to dashboard Cite

Abstract-The paper proposes the vicinities merging algorithm for prediction with side information. The algorithm is based on specialist experts techniques. We use vicinities in the side information domain to identify relevant past examples, apply standard learning techniques to them, and then use prediction with expert advice tools to merge those predictions. Guarantees from the theory of prediction with expert advice ensure that helpful vicinities are selected dynamically. The algorithm automatically converges on the right vicinities from an initial broad selection. We apply the resulting algorithms to two problems, prediction of implied volatility of options and prediction of students' performance at tests. On the problem of predicting implied volatility, the algorithm consistently outperforms naive competitors and a highly-tuned proprietary method used in the industry. When applied to the students' performance, the algorithm never falls behind the baseline and outperforms it when the side information is beneficial.

show abstract

Section: Specialist Expertsmentioning

confidence: 99%

“…In this paper we use methods from [7], [8] based on the aggregating algorithm introduced in [9], [10]. We hope the empirical studies of this paper will provide useful intuitions for the theory of prediction with expert advice.…”

Section: Introductionmentioning

confidence: 99%

Specialist Experts for Prediction with Side Information

Kalnishkan

Adamskiy

Chernov

et al. 2015

2015 IEEE International Conference on Data Mining Workshop (ICDMW)

Self Cite

View full text Add to dashboard Cite

show abstract

Prediction with Expert Advice under Discounted Loss

Chernov

Zhdanov

2010

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

Predictive Complexity and Generalized Entropy Rate of Stationary Ergodic Processes

Ghosh

Nandakumar

2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. In the online prediction framework, we use generalized entropy of to study the loss rate of predictors when outcomes are drawn according to stationary ergodic distributions over the binary alphabet. We show that the notion of generalized entropy of a regular game [10] is well-defined for stationary ergodic distributions. In proving this, we obtain new game-theoretic proofs of some classical information theoretic inequalities. Using Birkhoff's ergodic theorem and convergence properties of conditional distributions, we prove that a classical Shannon-McMillanBreiman theorem holds for a restricted class of regular games, when no computational constraints are imposed on the prediction strategies. If a game is mixable, then there is an optimal aggregating strategy which loses at most an additive constant when compared to any other lower semicomputable strategy. The loss incurred by this algorithm on an infinite sequence of outcomes is called its predictive complexity. We use our version of Shannon-McMillan-Breiman theorem to prove that when a restriced regular game has a predictive complexity, the predictive complexity converges to the generalized entropy of the game almost everywhere with respect to the stationary ergodic distribution.

show abstract

Supermartingales in prediction with expert advice

Cited by 5 publications

References 29 publications

Specialist Experts for Prediction with Side Information

Specialist Experts for Prediction with Side Information

Prediction with Expert Advice under Discounted Loss

Predictive Complexity and Generalized Entropy Rate of Stationary Ergodic Processes

Contact Info

Product

Resources

About