Machine Learning, Optimization & Statistics

  • Professor Chris Jermaine is the chair of the Rice University Department of Computer Science and the program director of the Data Science Initiative in the George R. Brown School of Engineering. He studies data analytics: how to analyze, store, retrieve, and manipulate large and heterogeneous data sets. Within this problem space, most of his work focuses on:  the systems-oriented problems that arise when building software to manage large and diverse data sets; and the difficulties that arise when applying statistical methods to such data sets. Much of his research is data-agnostic – concerned with building tools that can be used with many different types of data. He also have a particular interest in methods and tools for analyzing and managing data from certain domains, such as biomedical data and large, open-source source code repositories.
  • Professor Tasos Kyrillidis leads the OptimaLab. His research interests include optimization for machine learning, convex and non-convex algorithms and analysis, large-scale optimization, as well as any problem that includes a math-driven criterion, and requires an efficient method for its solution. One of his projects is new theories and algorithms for quantum system characterization. With more qubits, the volume of generated data outgrows our computational capacity of classical tomography methods, posing major challenges. The goal of this project is to close this gap, by investigating ways to accelerate such protocols, with guarantees.
  • Professor Santiago Segarra is the W. M. Rice Trustee Assistant Professor in the Department of Electrical and Computer Engineering. His research interests include Network Theory, Data Analysis, Machine Learning, and Graph Signal Processing. Examples of his research include (in Network Theory) proposing a network topology effective in recovering brain, social, financial and urban transportation networks using synthetic and real-world signals, and (in Machine Learning) developing Neural Network architectures for electricity consumption forecasting.
  • Professor Risa Myers is interested in exploring and innovating in data science pedagogy. She does this both through the development of interactive learning materials and by bringing lessons learned from research into the classroom in the form of examples, assignments, and exercises. Together with Lydia Kavraki and Chris Jermaine she has packaged a graduate level course on Data Science Tools & Models with an emphasis on healthcare data. Her research with the CEHI team is focused on data management in healthcare. There she explores approaches to making healthcare data more accessible and available.
  • Professor Anshumali Shrivastava's research focuses on Large Scale Machine Learning, Scalable and Sustainable Deep Learning, Randomized Algorithms for Big-Data and Graph Mining. In one of his recent projects, he created a cost-saving alternative to GPU, an algorithm called “sub-linear deep learning engine” (SLIDE), that uses general purpose central processing units (CPUs) without specialized acceleration hardware, overcoming a major obstacle in the burgeoning artificial intelligence industry by showing it is possible to speed up deep learning technology without specialized acceleration hardware like graphics processing units (GPUs).
  • Professor Devika Subramanian's research interests are in artificial intelligence and machine learning and their applications in computational systems biology, neuroscience of human learning, assessments of hurricane risks, network analysis of power grids, mortality prediction in cardiology, conflict forecasting and analysis of terrorist networks, and analysis of unstructured text data. One of her projects is aimed at the design and analysis of resource-bounded systems that adapt and learn from experience. She wrote the first paper defining the area of bounded optimality, i.e., what it means for an agent to make the “best” use of scarce resources. Her work centers on several applications designed to push the science of adaptive systems.
  • Professor Ron Goldman’s current research interests lie in the mathematical representation, manipulation, and analysis of shape using computers. He is particularly interested in algorithms for polynomial and piecewise polynomial curves and surfaces, and he has investigated both parametrically and implicitly represented geometry. His current work includes research in computer aided geometric design, solid modeling, computer graphics, subdivision, algorithmic algebraic geometry, probability and geometry, blossoming and polar forms, quartenions, dual quartenions, and clifford algebras, special functions and splines.
  • Professor Joe Warren’s primary research interest is in computer graphics and computational geometry protocols, with applications in Graphics and geometric modeling, Bioinformatics, Computer Gaming, and Education. He is actively interested in subdivision, a fractal-method for modeling smooth curves and surface. Subdivision surfaces are the industry-standard for entertainment and modeling applications. For bioinformatics, he help developed a 3D atlas for storing spatial gene expression patterns over the mouse brain.
  • Professor Maarten de Hoop’s research interests are in extracting subtle signal information from the ever-expanding data sets produced from advances in data acquisition by dense arrays and sensor technology. Maarten is interested in exploiting the foundations of the theory of seismic waves, their properties and multi-scale interaction with complex, highly heterogeneous media and nonlinear inverse theory, and in developing new paradigms for large-scale computing. There is a wide array of applications to his research, from upstream Oil and Gas reservoirs to exploration of Mars.
  • Professor Illya Hicks’ research interests are in combinatorial optimization, graph theory, and integer programming with applications in big data, imaging, social networks, cancer treatment, and logistics. In particular, he has done extensive research in finding cohesive groups in data networks and utilizing graph decomposition techniques to solve computationally difficult discrete optimization problems.
  • Professor Joey Huchette develops technology--both algorithms and software--for solving difficult decision-making problems. His primary research focus is the broad areas of operations research and mathematical optimization, with a particular emphasis on integer programming and discrete optimization. Much of his recent work has drawn on applied problems in machine learning and robotics and control.
  • Professor Andrew Schaefer’s research interests are in the broad area of operations research and industrial engineering. This includes mixed-integer programming, stochastic optimization and large-scale optimization.
  • Professors Andrew Schaefer and Professor Joey Huchette have won a National Institutes of Health-supported grant to develop a personalized approach to adaptive radiation therapy (ART) for head and neck cancers. The goal of the study is a tool to personalize chemo- and radiation-based therapies that both reduce risks to patients and make the process more efficient for providers.
  • Professor Matthias Heinkenschloss's research is concerned with the design and analysis of mathematical optimization algorithms for nonlinear, large-scale (often infinite dimensional) problems and their applications to science and engineering problems. Specific research areas include large-scale nonlinear optimization, model order reduction, optimal control of partial differential equations (PDEs), optimization under uncertainty, PDE constrained optimization, iterative solution of KKT systems, domain decomposition in optimization. Applications come in form of parameter identification, optimal control, or shape optimization problems.
  • Professor Richard Tapia is a member of the American Academy of Arts and Sciences, and the National Academy of Engineering. He holds the rank of University Professor, Rice’s highest academic title awarded to only seven individuals in the university’s history. He is a member of the Optimization Group at Rice university. His research focuses on providing best possible solutions to systems described by mathematical models. He has made distinguished contributions to the mathematical frontiers of optimization theory and numerical analysis, as well as inspiring underrepresented minority and female students in science and math.
  • Professor Yin Zhang’s research interests lie in the areas of optimization algorithms, compressive sensing: theory and algorithms, mathematical programming computation and applications and optimization applications in medicine and data science. In one of his previous projects, his work made it possible for NASA to successfully rotate the International Space Station by 90 degrees without using any costly fuel.
  • Professor Vicky Yao’s research focus is in computational biology, where she develops machine learning and statistical methods to improve our understanding of the biological circuitry that underlies living organisms and how its dysregulation may lead to disease. More specifically, she has worked on modeling tissue and cell type specificity as well as disease progression, both by developing general methods (such as semi-supervised network integration) and in applying them to decipher the molecular underpinnings of diseases such as Alzheimer’s, Parkinson’s, and rheumatoid arthritis.
  • Professor Michael Orchard leads research in image and video modeling and compression. In a recent work, he explores the development and the use of a complex-valued, multi-resolution image representation to model and exploit local image structures in image-processing applications. His approach distinguishes itself from prior approaches by constructing and exploiting the direct relationship between the locations of local structures and representation coefficients, leading to superb visual quality around interpolated localized structures.
  • Professor Dennis Cox’ primary research interests are nonparametric function estimation, functional data analysis, stochastic processes, machine learning, Bayesian methods, statistical computing, and the foundations and applications of statistical inferenence. He has collaborated with investigators from such disciplines as electrical engineering, neurophysiology, oncology, and nuclear fusion research. Professor Cox has also done theoretical work in nonparametric function estimation, statistical approximation theory, and Bayesian methods.
  • Professor Kathy Ensor is an expert in many areas of modern statistics, develops innovative statistical techniques to answer important questions in science, engineering and business with focus on the environment, energy and finance. She has developed methods for dependent data including: (1) Time series / Spatial and Spatial-Temporal / High-dimensional, (2) Unique applications of Bayesian Hierarchical Modeling and Approximate Bayesian Computation, and (3) Stochastic Process Modeling and Information Integration. The primary application areas include: (1) Statistical Finance, Risk Management and Energy, (2) Environmental Statistics, and Environmental Statistics+Public Health, and (3) Urban Analytics and creation of the Urban Data Platform for the greater Houston area through the Rice Kinder Institute for Urban Research.
  • Professor Rudy Guerra works in the areas biomedical, biostatistical and social science research. His biomedical interests include statistical genetics, bioinformatics, and imaging. He is also interested in applications of statistics in the social sciences, especially in education with a view toward inqualities and inquities. Of current interest is in determining how well modern methods of big data and machine learning work in social science problems, in particular of high-dimension and dependent structures.
  • Professor Marek Kimmel's research focuses on probabilistic modeling and statistical analysis in biosciences. He is particularly interested in applications of his work in cell and molecular biology and in cancer research. From the mathematical point of view, his interests lie in Markov and branching processes and in estimation theory. In recent years, Professor Kimmel has been researching gene amplification and rapid evolution of DNA, including such related questions as sequence and linkage analysis. Recently, these studies have gained importance and feasibility in connection with the Human Genome initiative.
  • Professor Daniel Kowal develops statistical methodology and algorithms for massive data sets with complex dependence structures, such as functional, time series, and spatial data. His recent work focuses on Bayesian models for prediction and inference, decision theory, discrete data analysis, and scalable approximations to complex models. He has been awarded the Rice Covid-19 research funds. He is building a predictive model or the trajectory of COVID-19 cases in Houston by borrowing information from locations that are similar to Houston and further along the disease incidence curve. The model is expected to improve the accuracy of real-time predictions and to inform key policy decisions.
  • Professor Meng Li’s recent research focuses on statistical modeling of challenging data that arise in scientific and industrial applications such as images, functional data, networks, and tree-structured data, with theoretical guarantees and scalable implementation. The theory and methods employed in his research include variable selection, image analysis, multiscale modeling, quantile regression, nonparametric Bayes, scalable algorithms, and functional data analysis.
  • Professor Erzsebet Merenyi focuses on understanding the structure of large, complex, high-dimensional data with neural computational intelligence techniques. She develops theoretical and simulation tools to discover and express relevant details of relationships in complicated data. Her research is motivated by real problems in Earth and planetary science, astronomy, and medicine. Her collaborative applications are in information extraction from remote sensing hyperspectral imagery, resource mapping, discovery, environmental diagnostics on planetary surfaces; generation of brain maps from functional MRI, analysis of clinical data; discovery from 21st century astronomical “big data”.
  • Professor Michael Schweinberger's research is concerned with the statistical analysis of complex, dependent, and high-dimensional data, first and foremost network data. Network data arise in, e.g., economics (e.g., contagion in financial markets), the health sciences (e.g., contagion of disease), biology (e.g., protein-protein interaction), political science (e.g., insurgencies), sociology (e.g., crime), machine learning (e.g., social networks, World Wide Web), and disaster and terrorism research. Owing to the dependent and high-dimensional nature of network data, the statistical analysis of network data gives rise to many conceptual, computational, and statistical challenges. His research has focused on tackling these conceptual, computational, and statistical challenges.
  • Professor David Scott's research interests focus on the analysis and understanding of data with many variables and cases. The research program encompasses basic theoretical studies of multivariate probability density estimation, computationally intensive algorithms in statistical computing, clustering, robust estimation, and data exploration using advanced techniques in computer visualization. In the field of nonparametric density estimation, Professor Scott has provided fundamental understanding of many estimators including the histogram, frequency polygon, averaged shifted histogram, discrete penalized-likelihood estimator, adaptive estimators, oversmoothed estimators, and modal and robust regression estimators. In the area of smoothing parameter selection, he has provided basic algorithms including biased cross-validation and multivariate cross-validation
  • Professor Marina Vannucci is interested in the development of statistical models for complex problems. Her methodological research has focused in particular on the theory and practice of Bayesian variable selection techniques and on the development of wavelet-based statistical models and their application. She also works in the areas of graphical models and nonparametric Bayes. Her research is often motivated by real problems that need to be addressed with suitable statistical methods. Methodologies developed by Dr. Vannucci have found applications in chemometrics and, more recently, in high-throughput genomics and in neuroimaging. Dr. Vannucci has also an interest in structural bioinformatics and, in particular, on the important problem of protein structure prediction.
  • Professor John Dobelman is currently Professor in the Practice in Statistics. His current research interests are stochastic modeling for markets and finance, simulation-based and quantitative portfolio selections and management, deception in patterns of noise, display of quantitative information, and improved communication.
  • Professor Philip Ernst’s research interests include applied probability, exact distribution theory, mathematical finance, mathematical statistics, operations research, optimal stopping, queueing systems, statistical inference for stochastic processes, and stochastic control. He is recognized for outstanding research accomplishments in operations research, probability and statistics, including solving a nearly 100-year old conjecture by Yule on nonsense correlation.
  • Professors John Dobelman, Kathy Ensor, Philip Ernst, and Daniel Kowal lead the Center for Computational Finance and Economic Systems (CoFES), dedicated to the quantitative study of financial markets and their ultimate impact on society. Since its founding in 2002, CoFES researchers have specialized in modeling dynamic microeconomic and macroeconomic systems, econometrics, and in the development of algorithms and forecasting techniques based on high-dimensional time-series data, artificial intelligence and machine learning, block chain technologies, Bayesian methods, and stochastic processes. The research emphasized by CoFES has evolved into new arenas in global markets and the financial technology landscape. Applications, which have benefited a wide cross section of industries, have included cutting-edge investment science, emerging markets, market trading, hedge funds, and financial risk management.
  • Professors Arko Barman and Su Chen are in Rice’s Data to Knowledge (D2K). The Rice D2K Lab provides students with engagement, enrichment, and experiential learning opportunities by connecting students with real-world data science challenges from companies, community organizations and researchers. Currently it is hosting projects on Covid-19 responses, data science for health, community and sustainability, energy and safety, as well as technology and innovation.
  • Professors Barbara Ostdiek’s research is in the Accounting field of the Jones Graduate School of Business, focusing on volatility and information flow, indicates that informational market linkages can be quite strong, that volatility is predictable, and that modeling cross-market linkages and volatility dynamics has economic value for market participants.