Sorry, you need to enable JavaScript to visit this website.

Generic Bounds on the Maximum Deviations in Sequential/Sequence Prediction (and the Implications in Recursive Algorithms and Learning/Generalization)

Primary tabs

Citation Author(s):
Song Fang, Quanyan Zhu
Submitted by:
Song Fang
Last updated:
24 October 2019 - 4:45pm
Document Type:
Poster
Document Year:
2019
Event:
Presenters Name:
Song Fang
Paper Code:
MLSP-137

Abstract 

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.

up
0 users have voted:

Dataset Files

postertemplate.pdf

(220)