Gökçesu, KaanManış, ErenKurt, Ali EmirhanYar, Ersin2018-04-122018-04-122017http://hdl.handle.net/11693/37584Date of Conference: 15-18 May 2017Conference Name: IEEE 25th Signal Processing and Communications Applications Conference, SIU 2017We investigate the estimation of distributions with time-varying parameters. We introduce an algorithm that achieves the optimal negative likelihood performance against the true probability distribution. We achieve this optimum regret performance without any knowledge about the total change of the parameters of true distribution. Our results are guaranteed to hold in an individual sequence manner such that we have no assumptions on the underlying sequences. Apart from the regret bounds, through synthetic and real life experiments, we demonstrate substantial performance gains with respect to the state-of-the-art probability density estimation algorithms in the literature.TurkishExponential familyIndividual sequence mannerNonstationary sourceSequential density estimationProbability density functionDensity estimationEstimation of distributionsProbability density estimationTime varying parameterProbability distributionsConference Paper10.1109/SIU.2017.7960588