TY - GEN
T1 - Generic Bounds on the Maximum Deviations in Sequential Prediction
T2 - 29th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2019
AU - Fang, Song
AU - Zhu, Quanyan
N1 - Funding Information:
This work was supported in part by NSF under grant ECCS-1847056 and SES-1541164, in part by a U. S. DOT grant through C2SMART Center at NYU, and in part by the U.S. DHS through the CIRI under Grant 2015-ST-061-CIRC01.
Publisher Copyright:
© 2019 IEEE.
PY - 2019/10
Y1 - 2019/10
N2 - 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.
AB - 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.
KW - Information-theoretic learning
KW - bounds on performance
KW - sequence prediction
KW - sequential learning
KW - sequential prediction
UR - http://www.scopus.com/inward/record.url?scp=85077707488&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85077707488&partnerID=8YFLogxK
U2 - 10.1109/MLSP.2019.8918758
DO - 10.1109/MLSP.2019.8918758
M3 - Conference contribution
AN - SCOPUS:85077707488
T3 - IEEE International Workshop on Machine Learning for Signal Processing, MLSP
BT - 2019 IEEE 29th International Workshop on Machine Learning for Signal Processing, MLSP 2019
PB - IEEE Computer Society
Y2 - 13 October 2019 through 16 October 2019
ER -