{"type":"ScholarlyArticle","title":"Confirmatory Bayesian Online Change Point Detection in the Covariance Structure of Gaussian Processes","authors":[{"name":"Jiyeon Han","slug":"jiyeon-han","given":"Jiyeon","family":"Han","affiliation":"Ulsan National Institute of Science and Technology"},{"name":"Kyowoon Lee","slug":"kyowoon-lee","given":"Kyowoon","family":"Lee","affiliation":"Ulsan National Institute of Science and Technology"},{"name":"Anh Tong","slug":"anh-tong","given":"Anh","family":"Tong","affiliation":"Ulsan National Institute of Science and Technology"},{"name":"Jaesik Choi","slug":"jaesik-choi","given":"Jaesik","family":"Choi","affiliation":"Ulsan National Institute of Science and Technology"}],"abstract":"In the analysis of sequential data, the detection of abrupt changes is important in predicting future events. In this paper, we propose statistical hypothesis tests for detecting covariance structure changes in locally smooth time series modeled by Gaussian Processes (GPs). We provide theoretically justified thresholds for the tests, and use them to improve Bayesian Online Change Point Detection (BOCPD) by confirming statistically significant changes and non-changes. Our Confirmatory BOCPD (CBOCPD) algorithm finds multiple structural breaks in GPs even when hyperparameters are not tuned precisely. We also provide conditions under which CBOCPD provides the lower prediction error compared to BOCPD. Experimental results on synthetic and real-world datasets show that our proposed algorithm outperforms existing methods for the prediction of nonstationarity in terms of both regression error and log-likelihood.","doi":"10.24963/ijcai.2019/340","url":"https://ijcai.org/proceedings/2019/340","pdf":"https://ijcai.org/proceedings/2019/0340.pdf","markdown":"https://ijcai.org/proceedings/2019/340.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/340","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Machine Learning A-L","track":"Main track","number":340,"pages":{"first":2449,"last":2455},"keywords":["Machine Learning: Probabilistic Machine Learning","Uncertainty in AI: Uncertainty in AI","Machine Learning: Time-series;Data Streams"],"videos":[],"references":[{"position":1,"raw":"[Adams and MacKay, 2007] Ryan Prescott Adams and David J.C. MacKay. Bayesian online changepoint detection. arXiv preprint arXiv:0710.3742, 2007.","title":"Bayesian online changepoint detection","authors":"Ryan Prescott, Adams, David J C Mackay","year":"2007","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Balek, 1977] Jaroslav Balek. Hydrology and Water Re- sources in Tropical Africa. Developments in water science. Elsevier Scientific Publishing Company, 1977.","title":"Hydrology and Water Resources in Tropical Africa","authors":"Jaroslav Balek, Balek","year":"1977","venue":"Developments in water science","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Barry and Hartigan, 1993] Daniel Barry and John A. Harti- gan. A bayesian analysis for change point problems. Jour- nal of the American Statistical Association, pages 309-319, 1993.","title":"A bayesian analysis for change point problems","authors":"Daniel Barry, John A Hartigan","year":"1993","venue":"Journal of the American Statistical Association","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chernoff and Zacks, 1964] Herman Chernoff and Shele- myahu Zacks. Estimating the current mean of a normal distribution which is subjected to changes in time. The Annals of Mathematical Statistics, pages 999-1018, 1964.","title":"Estimating the current mean of a normal distribution which is subjected to changes in time","authors":"Zacks Chernoff, Herman Chernoff, Shelemyahu Zacks","year":"1964","venue":"The Annals of Mathematical Statistics","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chow, 1960] Gregory C. Chow. Tests of equality between sets of coefficients in two linear regressions. Econometrica, pages 591-605, 1960.","title":"Tests of equality between sets of coefficients in two linear regressions","authors":"C Gregory, Chow","year":"1960","venue":"Econometrica","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Cleland et al., 2014] Ian Cleland, Manhyung Han, Chris Nu- gent, Hosung Lee, Sally McClean, Shuai Zhang, and Sungy- oung Lee. Evaluation of prompted annotation of activity data recorded from a smart phone. Sensors, pages 15861- 15879, 2014.","title":"Evaluation of prompted annotation of activity data recorded from a smart phone","authors":"Ian Cleland, Manhyung Han, Chris Nugent, Hosung Lee, Sally Mcclean, Shuai Zhang, Sungyoung Lee","year":"2014","venue":"Sensors","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Eric et al., 2008] Moulines Eric, Francis R. Bach, and Zaïd Harchaoui. Testing for homogeneity with kernel fisher discriminant analysis. In Proceedings of the Neural Infor- mation Processing Systems, pages 609-616, 2008.","title":"Testing for homogeneity with kernel fisher discriminant analysis","authors":"Moulines Eric, Francis R Bach, Zaïd Harchaoui","year":"2008","venue":"Proceedings of the Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Ewing and Malik, 2016] Bradley T. Ewing and Farooq Ma- lik. Volatility spillovers between oil prices and the stock market under structural breaks. Global Finance Journal, pages 12-23, 2016.","title":"Volatility spillovers between oil prices and the stock market under structural breaks","authors":"T Bradley, Farooq Ewing, Malik","year":"2016","venue":"Global Finance Journal","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Garnett et al., 2010] Roman Garnett, Michael A. Osborne, Steven Reece, Alex Rogers, and Stephen J. Roberts. Se- quential bayesian prediction in the presence of change- points and faults. The Computer Journal, pages 1430-1446, 2010.","title":"Sequential bayesian prediction in the presence of changepoints and faults","authors":"Garnett","year":"2010","venue":"The Computer Journal","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Gombay et al., 1996] Edit Gombay, Lajos Horváth, and Marie Husková. Estimators and tests for change in vari- ances. Statistics and Risk Modeling, pages 145-160, 1996.","title":"Estimators and tests for change in variances","authors":"Gombay","year":"1996","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Gretton et al., 2012] Arthur Gretton, Karsten M. Borgwardt, Malte J. Rasch, Bernhard Schölkopf, and Alexander Smola. A kernel two-sample test. Journal of Machine Learning Research, pages 723-773, 2012.","title":"A kernel two-sample test","authors":"Arthur Gretton, Karsten M Borgwardt, Malte J Rasch, Bernhard Schölkopf, Alexander Smola","year":"2012","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Isupova, 2017] Olga Isupova. Machine learning methods for behaviour analysis and anomaly detection in video. PhD thesis, University of Sheffield, 2017.","title":"Machine learning methods for behaviour analysis and anomaly detection in video","authors":"Olga Isupova","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Keshavarz et al., 2018] Hossein Keshavarz, Clayton Scott, and XuanLong Nguyen. Optimal change point detection in gaussian processes. Journal of Statistical Planning and Inference, pages 151-178, 2018.","title":"Optimal change point detection in gaussian processes","authors":"Hossein Keshavarz, Clayton Scott, Xuanlong Nguyen","year":"2018","venue":"Journal of Statistical Planning and Inference","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kim and Choi, 2015] Taehoon Kim and Jaesik Choi. Read- ing documents for bayesian online change point detection. In Proceedings of the Empirical Methods in Natural Lan- guage Processing, pages 1610-1619, 2015.","title":"Reading documents for bayesian online change point detection","authors":"Choi Kim, Taehoon Kim, Jaesik Choi","year":"2015","venue":"Proceedings of the Empirical Methods in Natural Language Processing","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Kim et al., 2009] Seung-Jean Kim, Kwangmoo Koh, Stephen Boyd, and Dimitry Gorinevsky. l 1 trend filtering. SIAM review, pages 339-360, 2009.","title":"l 1 trend filtering","authors":"Kim","year":"2009","venue":"SIAM review","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Li et al., 2015] Shuang Li, Yao Xie, Hanjun Dai, and Le Song. M-statistic for kernel change-point detection. In Proceedings of the Neural Information Processing Systems, pages 3366-3374, 2015.","title":"M-statistic for kernel change-point detection","authors":"Shuang Li, Yao Xie, Hanjun Dai, Le Song","year":"2015","venue":"Proceedings of the Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Manogaran and Lopez, 2018] Gunasekaran Manogaran and Daphne Lopez. Spatial cumulative sum algorithm with big data analytics for climate change detection. Computers and Electrical Engineering, pages 207-221, 2018.","title":"Spatial cumulative sum algorithm with big data analytics for climate change detection","authors":"Gunasekaran Manogaran, Daphne Lopez","year":"2018","venue":"Computers and Electrical Engineering","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Panda and Nayak, 2016] Soumya Priyadarsini Panda and Ajit Kumar Nayak. Automatic speech segmentation in syllable centric speech recognition system. International Journal of Speech Technology, pages 9-18, 2016.","title":"Automatic speech segmentation in syllable centric speech recognition system","authors":"Priyadarsini Soumya, Ajit Panda, Nayak Kumar","year":"2016","venue":"International Journal of Speech Technology","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Popper, 1951] William Popper. The Cairo Nilometer: Stud- ies in Ibn Taghrî Birdî's Chronicles of Egypt: I. Publica- tions in Semitic Philology. University of California Press, 1951.","title":"The Cairo Nilometer: Studies in Ibn Taghrî Birdî's Chronicles of Egypt: I","authors":"William Popper","year":"1951","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Saatc ¸i et al., 2010] Yunus Saatc ¸i, Ryan D. Turner, and Carl E. Rasmussen. Gaussian process change point models. In Proceedings of the International Conference on Machine Learning, pages 927-934, 2010.","title":"Gaussian process change point models","authors":"Saatc ¸i","year":"2010","venue":"Proceedings of the International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Sugiyama et al., 2008] Masashi Sugiyama, Taiji Suzuki, Shinichi Nakajima, Hisashi Kashima, Paul von Bünau, and Motoaki Kawanabe. Direct importance estimation for co- variate shift adaptation. Annals of the Institute of Statistical Mathematics, pages 699-746, 2008.","title":"Direct importance estimation for covariate shift adaptation","authors":"Sugiyama","year":"2008","venue":"Annals of the Institute of Statistical Mathematics","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Tewkesbury et al., 2015] Andrew P. Tewkesbury, Alexis J. Comber, Nicholas J. Tate, Alistair Lamb, and Peter F. Fisher. A critical synthesis of remotely sensed optical image change detection techniques. Remote Sensing of Environment, pages 1-14, 2015.","title":"A critical synthesis of remotely sensed optical image change detection techniques","authors":"Andrew P Tewkesbury, Alexis J Comber, Nicholas J Tate, Alistair Lamb, Peter F Fisher","year":"2015","venue":"Remote Sensing of Environment","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Xuan and Murphy, 2007] Xiang Xuan and Kevin Murphy. Modeling changing dependency structure in multivariate time series. In Proceedings of the International Conference on Machine Learning, pages 1055-1062, 2007.","title":"Modeling changing dependency structure in multivariate time series","authors":"Xiang Xuan, Kevin Murphy","year":"2007","venue":"Proceedings of the International Conference on Machine Learning","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}