Name
Title | ||
|---|---|---|
Generic Bounds On The Maximum Deviations In Sequential Prediction: An Information-Theoretic Analysis |
Abstract | ||
|---|---|---|
In this paper, we derive generic bounds on the maximum deviations in prediction errors for sequential prediction via an information-theoretic approach. The fundamental bounds are shown to depend only on the conditional entropy of the data point to be predicted given the previous data points. In the asymptotic case, the bounds are achieved if and only if the prediction error is white and uniformly distributed. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/MLSP.2019.8918758 | 2019 IEEE 29th International Workshop on Machine Learning for Signal Processing (MLSP) |
Keywords | Field | DocType |
Information-theoretic learning,sequential learning,sequential prediction,bounds on performance,sequence prediction | Sequence prediction,Data point,Mean squared prediction error,Random variable,Pattern recognition,Computer science,Algorithm,Stochastic process,If and only if,Artificial intelligence,Conditional entropy,Sequence learning | Conference |
ISSN | ISBN | Citations |
1551-2541 | 978-1-7281-0825-4 | 1 |
PageRank | References | Authors |
0.41 | 4 | 2 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Fang Song | 1 | 23 | 10.76 |
| Zhu Quanyan | 2 | 1295 | 116.31 |