Nonparametric Bayesian Estimation of Periodic Functions

Abstract

Many real world problems exhibit patterns that have periodic behavior. For example, in astrophysics, periodic variable stars play a pivotal role in understanding our universe. An important step when analyzing data from such processes is the problem of identifying the period: estimating the period of a periodic function based on noisy observations made at irregularly spaced time points. This problem is still a difficult challenge despite extensive study in different disciplines. The paper makes several contributions toward solving this problem. First, we present a nonparametric Bayesian model for period finding, based on Gaussian Processes (GP), that does not make strong assumptions on the shape of the periodic function. As our experiments demonstrate, the new model leads to significantly better results in period estimation when the target function is non-sinusoidal. Second, we develop a new algorithm for parameter optimization for GP which is useful when the likelihood function is very sensitive to the setting of the hyper-parameters with numerous local minima, as in the case of period estimation. The algorithm combines gradient optimization with grid search and incorporates several mechanisms to overcome the high complexity of inference with GP. Third, we develop a novel approach for using domain knowledge, in the form of a probabilistic generative model, and incorporate it into the period estimation algorithm. Experimental results on astrophysics data validate our approach showing significant improvement over the state of the art in this domain.

References in corpus (1)

• Period Estimation in Astronomical Time Series Using Slotted Correntropy

Cited by in corpus (16)

• Text Classification Algorithms: A Survey
• Understanding the Lomb-Scargle Periodogram
• Fast and scalable Gaussian process modeling with applications to astronomical time series
• A comparison of period finding algorithms
• Using conditional entropy to identify periodicity
• Vecchia approximations of Gaussian-process predictions
• Estimating activity cycles with probabilistic methods II. The Mount Wilson Ca H&K data
• A class of multi-resolution approximations for large spatial datasets
• Variability of Red Supergiants in M31 from the Palomar Transient Factory
• Looking at Blazar Light Curve Periodicities with Gaussian Processes
• Common dynamo scaling in slowly rotating young and evolved stars
• An Information Theoretic Algorithm for Finding Periodicities in Stellar Light Curves
• Modelling the Multiwavelength Variability of Mrk 335 using Gaussian Processes
• Period estimation for sparsely-sampled quasi-periodic light curves applied to Miras
• A Novel, Fully Automated Pipeline for Period Estimation in the EROS 2 Data Set
• Detection of Periodicity Based on Serial Dependence of Phase-Folded Data