Sequential prediction under incomplete feedback

Authors:
Gábor Lugosi
Affiliations:
ICREA and Department of Economics Business, Universitat Pompeu Fabra, Ramon Trias Fargas 25--27, 08005 Barcelona, Catalunya, Spain
Venue:
Proceedings of the 2007 conference on Artificial Intelligence Research and Development
Year:
2007

Citing 5
Cited 0

Prediction, Learning, and Games

Prediction, Learning, and Games
Regret Minimization Under Partial Monitoring

Mathematics of Operations Research
The On-Line Shortest Path Problem Under Partial Monitoring

The Journal of Machine Learning Research
Universal prediction

IEEE Transactions on Information Theory
Minimizing regret with label efficient prediction

IEEE Transactions on Information Theory

Quantified Score

Hi-index	0.00

Visualization

Abstract

We survey various variants of the randomized sequential forecasting problem when the forecaster has limited access to the past outcomes of the sequence to be predicted. This problem has various applications in on-line learning, learning in games, and information theory.