Digvijay Boob, Ph.D.

A headshot of Digvijay Boob, a member of the Lyle School of Engineering Faculty.

Digvijay Boob, Ph.D.

Assistant Professor, OREM

Office Location: 327 Caruth Hall

Send Email

 

Education

  • PhD in Algorithms, Combinatorics, and Optimization at Georgia Institute of Technology   

Biography

Dr. Digvijay Boob received his PhD in Algorithms, Combinatorics, and Optimization from Georgia Institute of Technology in 2020. He is serving as an assistant professor in Operations Research and Engineering Management department at Southern Methodist University since October 2020. He is interested in the design and analysis of optimization algorithms for convex as well as nonconvex optimization problems. He aims to develop novel algorithms which have provably faster convergence guarantees for large scale problems. Of particular interest are first-order algorithms, e.g., stochastic gradient descent, which have wide applications in various areas such as minimax games, differential privacy, stochastic optimization, and nonlinear programming. His research is supported by NSF grant. 

Honors & Awards

  • INFORMS Junior Faculty Interest Group paper competition, Finalist, 2021
  • INFORMS Optimization Society student paper competition, Second place, 2020
  • Alice and John Jarvis Student Research Award, Georgia Tech, Honorable mention, 2020
  • NeurIPS Oral presentation, 2019

Research 

  • Design and Analysis of Algorithms
  • First-order methods
  • Variational Inequality and Minmax problems
  • Data-driven (stochastic) optimization
  • Machine Learning Theory

Recent Publications

  • Mohammad Khalafi and Digvijay Boob, "Accelerated Primal-Dual Methods for Convex-Strongly-Concave Saddle Point Problems”, International Conference on Machine Learning (ICML), 2023.
  • Digvijay Boob and Cristobal Guzman, “Optimal algorithms for differentially private stochastic monotone variational inequalities and saddle-point problems”, Mathematical Programming, 2023.
  • Digvijay Boob, Qi Deng and Guanghui Lan, "Stochastic first-order methods for convex and nonconvex functional constrained optimization”, Mathematical Programming, 2022.
  • Digvijay Boob, Santanu Dey and Guaghui Lan, "Complexity of training relu neural network”, Discrete Optimization, 2022.
  • Tao Tantipongpipat, Chris Waites, Digvijay Boob, Amaresh Ankit Siva, Rachel Cummings, "Differentially private synthetic mixed-type data generation for unsupervised learning”, Intelligent Decision Systems, 2021.

Personal Website

https://sites.google.com/view/digvijaybb40