Elvan Ceyhan, PhD, College of Sciences and Mathematics Faculty and Staff

Professional Experience

Auburn University, Department of Mathematics & Statistics
Professor; Marguerite Scharnagle Endowed Professor — 2024–Present
Associate Professor — 2019–2024

• Co-Director, Consortium Center for Data Science Innovation (2024– )
• Lead roles in curriculum development (Bayesian Statistics, Statistical Inference sequences)
• Graduate mentor and supervisor for PhD and MS students
• Service on college and departmental committees, including search committees and prelim exam committees

Statistical and Applied Mathematical Sciences Institute (SAMSI), Research Triangle Park, NC
Deputy Director — 2017–2019

• Oversaw scientific programs, operations, budgeting, and postdoctoral mentoring
• Led interdisciplinary initiatives in climate statistics, precision medicine, and optimization
• Coordinated national workshops, professional development programs, and NSF site-visit preparation

North Carolina State University, Department of Statistics
Research Associate Professor — 2017–2019

• Taught undergraduate statistics and collaborated with SAMSI research programs

University of Pittsburgh, Department of Statistics
Visiting Associate Professor — 2016–2017

• Taught undergraduate and graduate statistics courses; engaged in departmental research seminars

Koç University, Istanbul, Turkey, Department of Mathematics
Associate Professor — 2011–2016
Assistant Professor — 2005–2011

• Served as Department Chair (2010–2011)
• Affiliated Faculty, Computational Sciences & Engineering Graduate Program
• Led curriculum reforms, supervised graduate students, and developed interdisciplinary teaching initiatives

Johns Hopkins University, Center for Imaging Science
Postdoctoral Fellow — 2004–2005

Innovation

Dr. Ceyhan’s research lies at the intersection of statistical machine learning, network science, and spatial data analysis. He develops graph- and network-based methods for classification, clustering, and pattern recognition, with emphasis on challenging settings such as class imbalance, structural overlap, and high-dimensional or spatially structured data. His foundational work on random geometric graphs—particularly proximity catch digraphs—has advanced both theory and algorithmic methodology for graph-based learning.

A second major research thrust focuses on network optimization under uncertainty, including the Canadian Traveler Problem and the Stochastic Obstacle Scene Problem. Dr. Ceyhan designs traversal algorithms and risk-aware decision frameworks for navigation in stochastic and adversarial environments, supported by NSF and ONR funding. His work integrates stochastic modeling, spatial point processes, Monte Carlo simulation, and optimization theory.

He also contributes to spatial statistics and biomedical data science, developing nearest-neighbor and graph-theoretic tools for spatial point pattern analysis and for modeling complex medical and neuroimaging data. Across these areas, his research blends theoretical development with computational implementation and applied collaborations in ecology, neuroscience, and engineering.

Keywords: statistical machine learning; graph-based learning; random geometric graphs; proximity catch digraphs; network optimization; stochastic traversal problems; spatial statistics; spatial point patterns; adversarial risk analysis; biomedical data analysis.