SKSebastian Kurtek

Sebastian Kurtek

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Sebastian Kurtek has a total of 65 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Elastic functional Cox regression model with shape predictors

    by Yi Tang Chen, Sebastian Kurtek

    Phase variability in functional data can obscure prominent geometric features, e.g. local extrema, and deteriorate predictive performance of regression models with functional predictors. We propose an elastic functional Cox regression model (EFCRM) that captures the association between a time-to-event outcome and the shape of a functional predictor. As such, EFCRM accounts for phase variation in the functional predictor via registration, which is supervised by the survival outcome. The model is fit using an iterative algorithm that alternates between removal of phase variation and estimation of the regression coefficient function. To improve convergence of the estimation procedure, we use a small number of separate gradient-based updates at each iteration for the two steps. The model is assessed based on estimation accuracy and predictive performance using a simulation study. We additionally apply the proposed framework to two real-world datasets. Overall, we show that the EFCRM is robust to misspecification of the number and type of basis functions used to approximate the coefficient function and results in comparable or better estimation accuracy and predictive ability than competitors.

  • Open Access

    Joint Registration and Conformal Prediction for Partially Observed Functional Data

    by Fangyi Wang, Sebastian Kurtek, Yuan Zhang

    1 IntroductionAccurate prediction of future trajectories given historical functional data is an important question in many applications. For instance, given previous (complete) daily observations o...

  • Open Access

    Sequential Bayesian Registration for Functional Data

    by Yoonji Kim, Oksana A. Chkrebtii, Sebastian A. Kurtek

    In many modern applications, discretely-observed data may be naturally understood as a set of functions. Functional data often exhibit two confounded sources of variability: amplitude (y-axis) and phase (x-axis). The extraction of amplitude and phase, a process known as registration, is essential in exploring the underlying structure of functional data in a variety of areas, from environmental monitoring to medical imaging. Critically, such data are often gathered sequentially with new functional observations arriving over time. Despite this, existing registration procedures do not sequentially update inference based on the new data, requiring model refitting. To address these challenges, we introduce a Bayesian framework for sequential registration of functional data, which updates statistical inference as new sets of functions are assimilated. This Bayesian model-based sequential learning approach utilizes sequential Monte Carlo sampling to recursively update the alignment of observed functions while accounting for associated uncertainty. Distributed computing significantly reduces computational cost relative to refitting the model using an iterative method such as Markov chain Monte Carlo on the full data. Simulation studies and comparisons reveal that the proposed approach performs well even when the target posterior distribution has a challenging structure. We apply the proposed method to three real datasets: (1) functions of annual drought intensity near Kaweah River in California, (2) annual sea surface salinity functions near Null Island, and (3) a sequence of repeated patterns in electrocardiogram signals.


  • Open Access

    Probabilistic size-and-shape functional mixed models

    by Fangyi Wang, Karthik Bharath, Oksana Chkrebtii, Sebastian Kurtek

    The reliable recovery and uncertainty quantification of a fixed effect function $μ$ in a functional mixed model, for modelling population- and object-level variability in noisily observed functional data, is a notoriously challenging task: variations along the $x$ and $y$ axes are confounded with additive measurement error, and cannot in general be disentangled. The question then as to what properties of $μ$ may be reliably recovered becomes important. We demonstrate that it is possible to recover the size-and-shape of a square-integrable $μ$ under a Bayesian functional mixed model. The size-and-shape of $μ$ is a geometric property invariant to a family of space-time unitary transformations, viewed as rotations of the Hilbert space, that jointly transform the $x$ and $y$ axes. A random object-level unitary transformation then captures size-and-shape \emph{preserving} deviations of $μ$ from an individual function, while a random linear term and measurement error capture size-and-shape \emph{altering} deviations. The model is regularized by appropriate priors on the unitary transformations, posterior summaries of which may then be suitably interpreted as optimal data-driven rotations of a fixed orthonormal basis for the Hilbert space. Our numerical experiments demonstrate utility of the proposed model, and superiority over the current state-of-the-art.

  • Open Access

    Assessment of Glioblastoma Multiforme Tumor Heterogeneity via MRI-Derived Shape and Intensity Features

    by Yi Tang Chen, Sebastian Kurtek

    We use a geometric approach to jointly characterize tumor shape and intensity along the tumor contour, as captured in magnetic resonance images, in the context of glioblastoma multiforme. Key properties of the proposed shape+intensity representation include invariance to translation, scale, rotation and reparameterization, which enable objective characterization and comparison of these crucial tumor features. The representation further allows the user to tune the emphasis of the shape and intensity components during registration, comparison and statistical summarization (averaging, computation of overall variance and exploration of variability via principal component analysis). In addition, we define a composite distance that is able to integrate shape and intensity information from two imaging modalities. The proposed framework can be integrated with distance-based clustering for the purpose of discovering groups of subjects with distinct survival prognosis. When applied to a cohort of subjects with glioblastoma multiforme, we discover groups with large median survival differences. We further tie the subjects’ cluster memberships to tumor heterogeneity. Our results suggest that tumor shape variation plays an important role in disease prognosis.


  • Topo-Geometric Analysis of Variability in Point Clouds Using Persistence Landscapes

    by James Matuk, Sebastian Kurtek, Karthik Bharath

    Topological data analysis provides a set of tools to uncover low-dimensional structure in noisy point clouds. Prominent amongst the tools is persistence homology, which summarizes birth-death times of homological features using data objects known as persistence diagrams. To better aid statistical analysis, a functional representation of the diagrams, known as persistence landscapes, enable use of functional data analysis and machine learning tools. Topological and geometric variabilities inherent in point clouds are confounded in both persistence diagrams and landscapes, and it is important to distinguish topological signal from noise to draw reliable conclusions on the structure of the point clouds when using persistence homology. We develop a framework for decomposing variability in persistence diagrams into topological signal and topological noise through alignment of persistence landscapes using an elastic Riemannian metric. Aligned landscapes (amplitude) isolate the topological signal. Reparameterizations used for landscape alignment (phase) are linked to a resolution parameter used to generate persistence diagrams, and capture topological noise in the form of geometric, global scaling and sampling variabilities. We illustrate the importance of decoupling topological signal and topological noise in persistence diagrams (landscapes) using several simulated examples. We also demonstrate that our approach provides novel insights in two real data studies.

  • Open Access

    Topo-Geometric Analysis of Variability in Point Clouds using Persistence Landscapes

    by James Matuk, Sebastian Kurtek, Karthik Bharath

    Topological data analysis provides a set of tools to uncover low-dimensional structure in noisy point clouds. Prominent amongst the tools is persistence homology, which summarizes birth-death times of homological features using data objects known as persistence diagrams. To better aid statistical analysis, a functional representation of the diagrams, known as persistence landscapes, enable use of functional data analysis and machine learning tools. Topological and geometric variabilities inherent in point clouds are confounded in both persistence diagrams and landscapes, and it is important to distinguish topological signal from noise to draw reliable conclusions on the structure of the point clouds when using persistence homology. We develop a framework for decomposing variability in persistence diagrams into topological signal and topological noise through alignment of persistence landscapes using an elastic Riemannian metric. Aligned landscapes (amplitude) isolate the topological signal. Reparameterizations used for landscape alignment (phase) are linked to a resolution parameter used to generate persistence diagrams, and capture topological noise in the form of geometric, global scaling and sampling variabilities. We illustrate the importance of decoupling topological signal and topological noise in persistence diagrams (landscapes) using several simulated examples. We also demonstrate that our approach provides novel insights in two real data studies.

  • Open Access

    Bayesian function registration with random truncation

    by Yi Lu, Radu Herbei, Sebastian Kurtek

    In this work, we develop a new set of Bayesian models to perform registration of real-valued functions. A Gaussian process prior is assigned to the parameter space of time warping functions, and a Markov chain Monte Carlo (MCMC) algorithm is utilized to explore the posterior distribution. While the proposed model can be defined on the infinite-dimensional function space in theory, dimension reduction is needed in practice because one cannot store an infinite-dimensional function on the computer. Existing Bayesian models often rely on some pre-specified, fixed truncation rule to achieve dimension reduction, either by fixing the grid size or the number of basis functions used to represent a functional object. In comparison, the new models in this paper randomize the truncation rule. Benefits of the new models include the ability to make inference on the smoothness of the functional parameters, a data-informative feature of the truncation rule, and the flexibility to control the amount of shape-alteration in the registration process. For instance, using both simulated and real data, we show that when the observed functions exhibit more local features, the posterior distribution on the warping functions automatically concentrates on a larger number of basis functions. Supporting materials including code and data to perform registration and reproduce some of the results presented herein are available online.

  • Geometric Deep Neural Network Using Rigid and Non-rigid Transformations for Landmark-based Human Behavior Analysis

    by Rasha Friji, Faten Chaieb, Hassen Drira, Sebastian Kurtek

    Deep learning architectures, albeit successful in most computer vision tasks, were designed for data with an underlying Euclidean structure, which is not usually fulfilled since pre-processed data may lie on a non-linear space. In this paper, we propose a geometric deep learning approach using rigid and non-rigid transformations, named KShapenet, for 2D and 3D landmark-based human motion analysis. Landmark configuration sequences are first modeled as trajectories on Kendall's shape space and then mapped to a linear tangent space. The resulting structured data are then input to a deep learning architecture, which includes a layer that optimizes over rigid and non-rigid transformations of landmark configurations, followed by a CNN-LSTM network. We apply KShapenet to 3D human landmark sequences for action and gait recognition, and 2D facial landmark sequences for expression recognition, and demonstrate the competitiveness of the proposed approach with respect to state-of-the-art.