Tirthankar DasGupta

Tirthankar DasGupta serves as Professor and Co-Director of Graduate Studies in the Department of Statistics within Rutgers University's School of Arts and Sciences. Previously an Assistant Professor (2008) and Associate Professor (2012) at Harvard University, he holds leadership roles in statistical methodology development and academic administration.

His educational foundation includes:

• Ph.D. in Industrial Engineering, Georgia Institute of Technology (2003-2007)
• Master of Technology in Quality, Reliability and Operations Research, Indian Statistical Institute (1991-1993)
• Master of Statistics in Applied Statistics and Data Analysis, Indian Statistical Institute (1989-1991)
• Bachelor of Science with Honors in Statistics, University of Calcutta (1986-1989)

Professor DasGupta's research centers on experimental design and causal inference with critical applications in nanotechnology and engineering systems. His work develops methodologies for sequential exploration of complex response surfaces, geometric shape error modeling, and quality engineering in additive manufacturing. Recent publications demonstrate sophisticated integration of statistical theory with physical sciences, particularly through deep learning-enhanced parameter optimization for molecular dynamics simulations.

His publication trajectory (2020-2025) reveals three dominant themes: (1) causal inference methods for complex experimental structures like split-plot designs and audit experiments; (2) minimum energy designs for response surface exploration with feasibility constraints; and (3) deep learning frameworks for ReaxFF force field parameterization in computational chemistry. These works consistently bridge theoretical statistics with nanotechnology and social science applications.

Key recognitions include:

• Sigma-Xi best doctoral thesis award
• David Pickard award from Harvard University for teaching excellence

He has advised seven doctoral students and secured major funding from NSF divisions (CMMI, DMS, SES) for projects including 'Geometric Shape Error Control for High-Precision Additive Manufacturing' and 'MATDAT18 Type-I: Machine Learning Framework for ReaxFF Optimization'. Current editorial roles include The Journal of the American Statistical Association and Journal of the Royal Statistical Society (Series B), building on prior service at Technometrics and Journal of Quality Technology.

His research integrates statistical methodology development with collaborative engineering projects, particularly in nanomaterial synthesis and additive manufacturing quality control through interdisciplinary teams funded by NSF initiatives.