I am a fourth-year Ph.D. candidate in Computer Science at Virginia Tech, working under the supervision of Dr. Sharath Raghvendra. I earned my B.Sc. in Computer Engineering from Sharif University of Technology. My research is at the intersection of theoretical computer science and machine learning, focusing on the development of efficient and provable algorithms for solving complex optimization problems. I am particularly interested in designing algorithms that are not only theoretically sound but also practical for real-world applications, especially in the domain of machine learning.
As a Ph.D. student, my work delves into fundamental problems in distribution comparison, a crucial task in various machine learning applications. My research specifically focuses on designing efficient algorithms for computing optimal transport—a key concept in ML—and introducing new robust metrics that enhance the accuracy and reliability of distribution comparisons. By bridging the gap between theory and practice, I aim to develop tools and methodologies that can be directly applied to advance machine learning systems and other computational fields.
*Authors ordered alphabetically.
[SODA 25]*
P. K. Agarwal, S. Raghvendra, P. Shirzadian, K. Yao, ”An Efficient Approximation Algorithm for Computing Wasserstein Barycenter Under Euclidean Metric” Accepted to ACM-SIAM Symposium on Discrete Algorithms, 2025.
Links: [Paper]
[NeurIPS 24]*
P. K. Agarwal, S. Raghvendra, P. Shirzadian, K. Yao, ”A Combinatorial Algorithm for the Semi-Discrete Optimal Transport Problem.” Accepted to Advances in Neural Information Processing Systems, 2024.
Links: [Paper | Presentation ]
[ICML 24]*
S. Raghvendra, P. Shirzadian, K. Zhang. ”A New Robust Partial p-Wasserstein-Based Metric for Comparing Distributions.” In Proc. 41st International Conference on Machine Learning, 2024.
Links: [Paper | Presentation | Poster]
[SODA 24]*
P. K. Agarwal, S. Raghvendra, P. Shirzadian, K. Yao, “Fast and Accurate Approximations of the Optimal Transport in Semi-Discrete and Discrete Settings”, In Proc. ACM-SIAM Symposium on Discrete Algorithms, 2024.
Links: [Paper]
[NeurIPS 23]*
A. G. Gattani, S. Raghvendra, P. Shirzadian, “A Robust Exact Algorithm for the Euclidean Bipartite Matching Problem”, In Proc. Advances in Neural Information Processing Systems, 2023.
Links: [Paper | Presentation | Poster]
[ICLR 23]*
P. K. Agarwal, S. Raghvendra, P. Shirzadian, and R. Sowle, “A Higher Precision Algorithm for Computing the 1-Wasserstein Distance”, In Proc. 11th International Conference on Learning Representations, 2023. Accepted as notable top 25%.
Links: [Paper | Presentation]
[Sci.Rep 23]
P. Shirzadian, B. Antony, A. G. Gattani, N. Tasnina, and L. S. Heath, “A Time Evolving Online Social Network Generation Algorithm”, Scientific Reports, vol. 13, no. 1, p. 2395, 2023.
Links: [Paper]
[SWAT 22]*
P. K. Agarwal, S. Raghvendra, P. Shirzadian, and R. Sowle, “An Improved ε-Approximation Algorithm for Geometric Bipartite Matching”, In Proc. 18th Scandinavian Symposium and Workshops on Algorithm Theory (SWAT), 2022.
Links: [Paper]
[Eng.Com 22]
M. Tajdari, F. Tajdari, P. Shirzadian, A. Pawar, et. al., “Next-Generation Prognosis Framework for Pediatric Spinal Deformities Using Bio-Informed Deep Learning Networks”, Engineering with Computers, pp. 1–24, 2022.
Links: [Paper]