Samuel Talkington
I am a Ph.D. student in the School of Electrical and Computer Engineering at the Georgia Institute of Technology, and I am fortunate to be advised by Daniel K. Molzahn.
At the interface of statistics and optimization, my research develops efficient algorithms for societal-scale problems in electric power networks. I exploit domain structure—such as power flow physics, spectral graph properties, and communication protocols—to improve scalability and reliability. My broader vision is to treat randomness as a resource to transform how the grid is operated, drawing on tools such as randomized numerical linear algebra.
I am privileged for my work to be supported by the NSF Graduate Research Fellowship (GRF), the NSF AI Institute for Advances in Optimization (AI4OPT), the Georgia Tech Supporting Teaching ExpERience (STEER) fellowship, Sandia National Laboratories, the Georgia Tech Strategic Energy Institute (SEI), the Georgia Tech Energy Policy and Innovation Center (EPICenter), and the Georgia Tech Szalm ECE Fellowship.
On the academic job market in Fall 2025
Please contact me if you would like to discuss opportunities to work together.
Statements available upon request.
Blog
Harvard PAI Seminar: "Randomness as a Resource: Scalable Algorithms for Grid Decision-Making"Generating Random Multigraphs and Laplacians in Julia
Differentiating Solutions of DC Optimal Power Flow
Writing DC Optimal Power Flow in Matrix Form
all posts
Recent Research
Error Bounds for Radial Network Topology Learning from Quantized Measurements
Samuel Talkington, Aditya Rangarajan, Pedro A. de Alcântara, Line Roald, Daniel K. Molzahn, and Daniel R. Fuhrmann
arXiv / bibTeX
VArsity: Can Large Language Models Keep Power Engineering Students in Phase?
Samuel Talkington and Daniel K. Molzahn
arXiv / bibTeX
Covert Distribution Load Tripping Attacks
Betelihem Kebede Ashebo, Samuel Talkington, Saman Zonouz, and Daniel K. Molzahn
preprint / code / bibTeX
Classifying Reactive Power Control Laws of Behind-the-Meter Solar Photovoltaic Inverters
Richard Asiamah, Samuel Talkington, Michael Boateng, Marta Vanin, Frederik Geth, and Daniel K. Molzahn
Kansas Power and Energy Conference (KPEC) / bibTeX
Srategic Electric Distribution Network Sensing via Spectral Bandits
Samuel Talkington, Rahul Gupta, Richard Asiamah, Paprapee Buason, and Daniel K. Molzahn
IEEE CDC 2024 / arXiv / slides / bibTeX
Locational marginal burden: Quantifying the equity of optimal power flow solutions
Samuel Talkington∗, Amanda West∗, and Rabab Haider (∗ equal contribution)
ACM e-Energy 2024 / arXiv / slides / bibTeX