Title :
Asymptotics of predictive stochastic complexity
Author :
Gerencser, Laszlo
Author_Institution :
Comput Vision & Robotics Lab., McGill Univ., Montreal, Que., Canada
Abstract :
This paper presents the basic ideas of the theory of stochastic complexity with rigorous asymptotic results in the field of time-series analysis and system identification, which demonstrate the applicability of stochastic complexity to these difficult statistical problems
Keywords :
computational complexity; filtering and prediction theory; identification; statistical analysis; stochastic systems; time series; asymptotic results; predictive stochastic complexity; statistical problems; system identification; time-series analysis; Computer vision; Density functional theory; Intelligent robots; Laboratories; Robot vision systems; Robotics and automation; Stochastic processes; Stochastic systems; Telephony; Time series analysis;
Conference_Titel :
Data Compression Conference, 1991. DCC '91.
Conference_Location :
Snowbird, UT
Print_ISBN :
0-8186-9202-2
DOI :
10.1109/DCC.1991.213358
