Probability theory for the Brier game

Theoretical Computer Science

Volumn 261, Issue 1, 2001, Pages 57-79

  Vovk, V ^a  

^a UNIVERSITY OF LONDON   (United Kingdom)

Author keywords

Kolmogorov complexity; Limit theorems of probability theory; Prediction with expert advice

Indexed keywords

EXPERT SYSTEMS; GAME THEORY; PROBABILITY;

KOLMOGOROV COMPLEXITY;

COMPUTATIONAL COMPLEXITY;

EID: 0034920708     PISSN: 03043975     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0304-3975(00)00133-X     Document Type: Conference Paper

References (24)

1. Worst-case quadratic loss bounds for on-line prediction of linear functions by gradient descent
2. Universal portfolios with side information
3. Calibration-based empirical probability
4. Prequential probability: Principles and properties
5. Learning probabilistic prediction functions
6. Sequential prediction of individual sequences under general loss functions
7. Tracking the best expert
8. Additive versus exponentiated gradient updates for linear prediction
9. On-line learning of linear functions
10. The weighted majority algorithm
11. An extension of Borel determinacy
12. Complexity-based induction systems: Comparison and convergence theorems
13. On a randomness criterion
14. Aggregating strategies
15. A logic of probability, with application to the foundations of statistics
16. A game of prediction with expert advice
17. Derandomizing stochastic prediction strategies
18. Competitive on-line linear regression