Piotr Fryzlewicz's Publications and Software
Preprints (year in brackets refers to the latest version)
A change-point approach to estimating the proportion of false null hypotheses in multiple testing. A. Kostic and P. Fryzlewicz (2023). In submission. Software (R package MTCP)
Fast and optimal inference for change points in piecewise polynomials via differencing. S. Gavioli-Akilagun and P. Fryzlewicz (2023). In submission. Software (R package ChangePointInference) and code for reproducing the numerical results
Doubly inhomogeneous reinforcement learning. L. Hu, M. Li, C. Shi, Z. Wu and P. Fryzlewicz (2022). In submission.
Testing stationarity and change point detection in reinforcement learning. M. Li, C. Shi, Z. Wu and P. Fryzlewicz (2022). In submission. Software
Multiscale autoregression on adaptively detected timescales. R. Baranowski, Y. Chen and P. Fryzlewicz (2024). With supplement. Under revision. Software (R package amar)
Book
Change-point Detection and Data Segmentation - forthcoming book by P. Fearnhead and P. Fryzlewicz. Chapters posted here by the permission of the publisher. Any comments welcome.

Chapter 3 - Detecting A Single Change-point
In Journals
Robust Narrowest Significance Pursuit: Inference for multiple change-points in the median. P. Fryzlewicz (2024). Journal of Business and Economic Statistics, to appear. Software
Multiple change point detection under serial dependence: Wild contrast maximisation and gappy Schwarz algorithm. H. Cho and P. Fryzlewicz (2024). Journal of Time Series Analysis, to appear. Software
Automatic change-point detection in time series via deep learning. J. Li, P. Fearnhead, P. Fryzlewicz and T. Wang (2024). Journal of the Royal Statistical Society Series B (with discussion), to appear. Software
Detecting linear trend changes in data sequences. H. Maeng and P. Fryzlewicz (2024). With supplement. Statistical Papers, to appear. Software (R package trendsegmentR)
Narrowest Significance Pursuit: inference for multiple change-points in linear models. P. Fryzlewicz (2024). With supplement. Journal of the American Statistical Association, to appear. Software: R package nsp; see also zipped R code and data for reproducing the results reported in the paper
Detection of multiple structural breaks in large covariance matrices. Y. Li, D. Li and P. Fryzlewicz (2023). With supplement. Journal of Business and Economic Statistics, 41, 846-861. Software (R package BSCOV)
Exploiting disagreement between high-dimensional variable selectors for uncertainty visualization. C. Yuen and P. Fryzlewicz (2022). With supplement. Journal of Computational and Graphical Statistics, 31, 351-359. Software: R package CSUV and Shiny app csuv
Cross-covariance isolate detect: a new change-point method for estimating dynamic functional connectivity. A. Anastasiou, I. Cribben and P. Fryzlewicz (2022). Medical Image Analysis, 75, 102252. Software (R package ccid)
Detecting multiple generalized change-points by isolating single ones. A. Anastasiou and P. Fryzlewicz (2022). With supplement. Metrika, 85, 141-174. Software: R package breakfast; also in the older package IDetect.
Regularizing axis-aligned ensembles via data rotations that favor simpler learners. R. Blaser and P. Fryzlewicz (2021). Statistics and Computing, 31, 15. Software (R package random.rotation)
Detecting possibly frequent change-points: Wild Binary Segmentation 2 and steepest-drop model selection. P. Fryzlewicz (2020). Journal of the Korean Statistical Society (with discussion), 49, 1027-1070. Rejoinder, 49, 1099-1105. Software: R package breakfast; extra features in alpha version on Github.
Ranking-Based Variable Selection for high-dimensional data. R. Baranowski, Y. Chen and P. Fryzlewicz (2020). With supplement. Statistica Sinica, 30, 1485-1516. Software (R package rbvs)
Detection of gamma-ray transients with wild binary segmentation. S. Antier, K. Barynova, P. Fryzlewicz, C. Lachaud and G. Marchal-Duval (2020). Monthly Notices of the Royal Astronomical Society, 493, 4428-4441.
Predictive, finite-sample model choice for time series under stationarity and non-stationarity. T. Kley, P. Preuss and P. Fryzlewicz (2019). Electronic Journal of Statistics, 13, 3710-3774. Software (R package forecastSNSTS)
NOVELIST estimator of large correlation and covariance matrices and their inverses. N. Huang and P. Fryzlewicz (2019). Test, 28, 694-727. Software (R package novelist)
Regularized forecasting via smooth-rough partitioning of the regression coefficients. H. Maeng and P. Fryzlewicz (2019). Electronic Journal of Statistics, 13, 2093-2120. Software (R package srp)
Narrowest-Over-Threshold detection of multiple change-points and change-point-like features. R. Baranowski, Y. Chen and P. Fryzlewicz (2019). With supplement. Journal of the Royal Statistical Society Series B, 81, 649-672. Software: R package breakfast; also in the older package not.
Likelihood ratio Haar variance stabilization and normalization for Poisson and other non-Gaussian noise removal. P. Fryzlewicz (2018). Statistica Sinica, 28 (special issue in memory of Prof. Peter Hall), 2885-2901.
Tail-greedy bottom-up data decompositions and fast multiple change-point detection. P. Fryzlewicz (2018). With supplement. Annals of Statistics, 46, 3390-3421. Software (R package breakfast)
Simultaneous multiple change-point and factor analysis for high-dimensional time series. M. Barigozzi, H. Cho and P. Fryzlewicz (2018). With supplement. Journal of Econometrics, 206, 187-225. Software (R package factorcpt)
Complex-valued wavelet lifting and applications. J. Hamilton, M. Nunes, M. Knight and P. Fryzlewicz (2018). Technometrics, 60, 48-60. Software
Multiple change-point detection for non-stationary time series using Wild Binary Segmentation. K. Korkas and P. Fryzlewicz (2017). Statistica Sinica, 27, 287-311. Software (R package wbsts)
SHAH: SHape-Adaptive Haar wavelets for image processing. P. Fryzlewicz and C. Timmermans (2016). Journal of Computational and Graphical Statistics, 25, 879-898. Software
Random rotation ensembles. R. Blaser and P. Fryzlewicz (2016). Journal of Machine Learning Research, 17, 1-26. Software (R package random.rotation)
Relative liquidity and future volatility. M. Valenzuela, I. Zer, P. Fryzlewicz and T. Rheinländer (2015). Journal of Financial Markets, 24, 25-48.
Multiple change-point detection for high-dimensional time series via Sparsified Binary Segmentation. H. Cho and P. Fryzlewicz (2015). Journal of the Royal Statistical Society Series B, 77, 475-507. Software (R package hdbinseg)
Wild Binary Segmentation for multiple change-point detection. P. Fryzlewicz (2014). Annals of Statistics, 42, 2243-2281. Software: R package breakfast; also in the older package wbs.
Multiple-change-point detection for auto-regressive conditional heteroscedastic processes. P. Fryzlewicz and S. Subba Rao (2014). Journal of the Royal Statistical Society Series B, 76, 903-924. Software
Adaptive trend estimation in financial time series via multiscale change-point-induced basis recovery. A. L. Schroeder and P. Fryzlewicz (2013). Statistics and Its Interface, 6, 449-461.
High-dimensional volatility matrix estimation via wavelets and thresholding. P. Fryzlewicz (2013). Biometrika, 100, 921-938.
A reflection of history: fluctuations in Greek sovereign risk between 1914 and 1929. O. Christodoulaki, H. Cho and P. Fryzlewicz (2012). European Review of Economic History, 16, 550-571.
High-dimensional variable selection via tilting. H. Cho and P. Fryzlewicz (2012). Journal of the Royal Statistical Society Series B, 74, 593-622. Software (R package tilting)
Time-Threshold Maps: using information from wavelet reconstructions with all threshold values simultaneously. P. Fryzlewicz (2012). Journal of the Korean Statistical Society (with discussion), 41, 145-159. Rejoinder: Time-Threshold Maps: using information from wavelet reconstructions with all threshold values simultaneously. P. Fryzlewicz (2012). Journal of the Korean Statistical Society, 41, 173-175.
Multiscale and multilevel technique for consistent segmentation of nonstationary time series. H. Cho and P. Fryzlewicz (2012). Statistica Sinica, 22, 207-229. Software
Multiscale interpretation of taut string estimation and its connection to Unbalanced Haar wavelets. H. Cho and P. Fryzlewicz (2011). Statistics and Computing, 21, 671-681.
Thick-pen transformation for time series. P. Fryzlewicz and H.-S. Oh (2011). Journal of the Royal Statistical Society Series B, 73, 499-529.
Mixing properties of ARCH and time-varying ARCH processes. P. Fryzlewicz and S. Subba Rao (2011). Bernoulli, 17, 320-346.
The Dantzig selector in Cox's proportional hazards model. A. Antoniadis, P. Fryzlewicz and F. Letue (2010). Scandinavian Journal of Statistics, 37, 531-552. See also this corrigendum. Software
Estimating linear dependence between nonstationary time series using the locally stationary wavelet model. J. Sanderson, P. Fryzlewicz and M. Jones (2010). Biometrika, 97, 435-446.
Consistent classification of nonstationary time series using stochastic wavelet representations. P. Fryzlewicz and H. Ombao (2009). Journal of the American Statistical Association, 104, 299-312.
Data-driven wavelet-Fisz methodology for nonparametric function estimation. P. Fryzlewicz (2008). Electronic Journal of Statistics, 2, 863-896. Software
A wavelet-Fisz approach to spectrum estimation. P. Fryzlewicz, G. Nason and R. von Sachs (2008). Journal of Time Series Analysis, 29, 868-880.
Normalized least-squares estimation in time-varying ARCH models. P. Fryzlewicz, T. Sapatinas and S. Subba Rao (2008). Annals of Statistics, 36, 742-786.
Unbalanced Haar technique for nonparametric function estimation. P. Fryzlewicz (2007). Journal of the American Statistical Association, 102, 1318-1327. Software (R package unbalhaar)
Bivariate hard thresholding in wavelet function estimation. P. Fryzlewicz (2007). Statistica Sinica, 17, 1457-1481. Software
GOES-8 X-ray sensor variance stabilization using the multiscale data-driven Haar-Fisz transform. P. Fryzlewicz, V. Delouille and G. Nason (2007). Journal of the Royal Statistical Society Series C, 56, 99-116.
Variance stabilization and normalization for one-color microarray data using a data-driven multiscale approach. E. Motakis, G. Nason, P. Fryzlewicz and G. Rutter (2006). Bioinformatics, 22, 2547-2553. Software (R package DDHFm)
A Haar-Fisz technique for locally stationary volatility estimation. P. Fryzlewicz, T. Sapatinas and S. Subba Rao (2006). Biometrika, 93, 687-704.
Haar-Fisz estimation of evolutionary wavelet spectra. P. Fryzlewicz and G. Nason (2006). Journal of the Royal Statistical Society Series B, 68, 611-634. Software
Parametric modelling of thresholds across scales in wavelet regression. A. Antoniadis and P. Fryzlewicz (2006). Biometrika, 93, 465-471. Software
Modelling and forecasting financial log-returns as locally stationary wavelet processes. P. Fryzlewicz (2005). Journal of Applied Statistics, 32, 503-528. Software
A Haar-Fisz algorithm for Poisson intensity estimation. P. Fryzlewicz and G. Nason (2004). Journal of Computational and Graphical Statistics, 13, 621-638. Software
Forecasting non-stationary time series by wavelet process modelling. P. Fryzlewicz, S. Van Bellegem and R. von Sachs (2003). Annals of the Institute of Statistical Mathematics, 55, 737-764. Software
Other
Multiscale network analysis through tail-greedy bottom-up approximation, with applications in neuroscience. X. Kang, P. Fryzlewicz, C. Chu, M. Kramer and E. Kolaczyk (2018). Proceedings of 2017 51st Asilomar Conference on Signals, Systems and Computers, 29 October-1 November 2017, DOI: 10.1109/ACSSC.2017.8335617. Software
Invited discussion of "Random projection ensemble classification" by Cannings and Samworth. R. Blaser and P. Fryzlewicz (2017). Journal of the Royal Statistical Society Series B, 79, 1007.
Invited discussion of "Statistical modelling of citation exchange between statistics journals" by Varin, Cattelan and Firth. P. Fryzlewicz (2016). Journal of the Royal Statistical Society Series A, 179, 49-51.
Discussion of "Multiscale change point inference" by Frick, Munk and Sieling. P. Fryzlewicz (2014). Journal of the Royal Statistical Society Series B, 76, 547-548.
On multi-zoom autoregressive time series models. P. Fryzlewicz (2013). Oberwolfach Reports 48/2013, 21-24.
Invited discussion of "Large covariance estimation by thresholding principal orthogonal complements" by Fan, Liao and Mincheva. P. Fryzlewicz and N. Huang (2013). Journal of the Royal Statistical Society Series B, 75, 648-650.
Wavelet methods. P. Fryzlewicz (2010). Invited overview paper in Wiley Interdisciplinary Reviews: Computational Statistics, 2, 654-667.
On the thick-pen transformation for time series. P. Fryzlewicz (2010). Oberwolfach Reports 05/2010, 27-30.
Multiscale breakpoint detection in piecewise stationary AR models. H. Cho and P. Fryzlewicz (2008). Proceedings of IASC 2008, Yokohama, Japan, 5-8 December 2008.
Locally stationary wavelet coherence with application to neuroscience. J. Sanderson and P. Fryzlewicz (2007). Proceedings of the 56th Session of the International Statistical Institute, Lisbon, Portugal, 22-29 August 2007.
Locally stationary wavelet coherence with application to neuroscience. J. Sanderson and P. Fryzlewicz (2007). Proceedings of the LASR 2007 Workshop - Systems Biology and Statistical Bioinformatics, Leeds, UK, 4-6 July 2007.
A data-driven Haar-Fisz transform for multiscale variance stabilization. P. Fryzlewicz and V. Delouille (2005). Proceedings of the 13th IEEE/SP Workshop on Statistical Signal Processing, 17-20 July 2005.
A wavelet-based model for forecasting non-stationary processes. S. Van Bellegem, P. Fryzlewicz and R. von Sachs (2003). In GROUP 24: Physical and Mathematical Aspects of Symmetries, Eds. J-P. Gazeau, R. Kerner, J-P. Antoine, S. Metens, J-Y. Thibon; IOP Publishing, Bristol. Figure
Theses
Wavelet Techniques for Time Series and Poisson Data. P. Fryzlewicz (2003). Ph.D. Thesis, Department of Mathematics, University of Bristol, UK. Software
The Application of Linear Programming to American Option Valuation in the Jump-Diffusion Model. P. Fryzlewicz (2000). M. Sc. Dissertation, Department of Mathematics, Wroclaw University of Technology, Poland.


home