Prediction with Expert Advice under Discounted Loss
From MaRDI portal
Abstract: We study prediction with expert advice in the setting where the losses are accumulated with some discounting---the impact of old losses may gradually vanish. We generalize the Aggregating Algorithm and the Aggregating Algorithm for Regression to this case, propose a suitable new variant of exponential weights algorithm, and prove respective loss bounds.
Recommendations
- Towards optimal algorithms for prediction with expert advice
- Prediction with expert advice: a PDE perspective
- Prediction with expert evaluators' advice
- Supermartingales in Prediction with Expert Advice
- Supermartingales in prediction with expert advice
- Algorithmic Learning Theory
- Prediction based on a discrete dynamic model using expert information
- On the asymptotic optimality of the comb strategy for prediction with expert advice
- Improved second-order bounds for prediction with expert advice
- Learning Theory
Cited in
(12)- Aggregating algorithm for prediction of packs
- Improved second-order bounds for prediction with expert advice
- Online prediction problems with variation
- Supermartingales in Prediction with Expert Advice
- Aggregating Algorithm for a Space of Analytic Functions
- Learning Volatility of Discrete Time Series Using Prediction with Expert Advice
- Finite-time 4-expert prediction problem
- scientific article; zbMATH DE number 7064063 (Why is no real title available?)
- Algorithmic Learning Theory
- Optimal discovery with probabilistic expert advice: finite time analysis and macroscopic optimality
- Algorithmic Learning Theory
- Forecasting wind power ramps with prediction coordinates
This page was built for publication: Prediction with Expert Advice under Discounted Loss
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4930703)