Gerald D. McInvale Early Career Professor and
Assistant Professor
Education
- Ph.D. Electrical Engineering and Computer Sciences (2020), University of California, Berkeley
- B.Tech. Electrical Engineering (2014), Indian Institute of Technology, Madras
Expertise
- High-dimensional statistics
- Statistical machine learning
- Mathematical Programming
- Information theory
- Reinforcement learning
About
Ashwin Pananjady is a Gerald D. McInvale Early Career Professor and Assistant Professor at Georgia Tech with a joint appointment between the H. Milton Stewart School of Industrial and Systems Engineering and the School of Electrical and Computer Engineering. He is also a Gary C. Butler Family Faculty Fellow. He received his Ph.D. from the Department of Electrical Engineering and Computer Sciences (EECS) at the University of California Berkeley, where he was awarded the David J. Sakrison Memorial Prize for his dissertation research, and the B.Tech. degree in Electrical Engineering from the Indian Institute of Technology Madras, where he graduated with the Governor's Gold Medal.
Research
Pananjady's research interests lie broadly in statistics, optimization, signal processing and information theory, as well as their applications in data science, machine learning, and reinforcement learning. He is particularly interested in statistical and computational problems arising from high-dimensional data with geometric structure. His research spanning these topics has received early career awards such as the New Researcher Award (honorable mention) from the Bernoulli Society and the Lawrence Brown award from the Institute of Mathematical Statistics, paper recognitions such as a best paper prize (runner-up) for Young Researchers in Continuous Optimization from the Mathematical Optimization Society and an Outstanding Paper Award from the Algorithmic Learning Theory conference, industry awards such as the Adobe Data Science Research Award, Amazon Research Award and Google Research Scholar Award, and a Simons-Berkeley Research Fellowship in Probability, Geometry and Computation in High Dimensions.
Teaching
Pananjady teaches classes at the undergraduate, Masters and PhD levels across the schools of ISyE and ECE in machine learning and data science. He has created a new advanced undergraduate course called "Foundations of Modern Data Science" in ISYE and an advanced graduate course on "High dimensional statistics, signal processing and optimization" in ECE.
Representative Publications
- Accurate, provable, and fast polychromatic tomographic reconstruction: A variational inequality approach, Mengqi Lou, Kabir Verchand, Sara Fridovich-Keil, Ashwin Pananjady. SIAM Journal on Imaging Sciences (SIIMS), 2026+.
- Hyperparameter tuning via trajectory predictions: Stochastic prox-linear methods in matrix sensing, Mengqi Lou, Kabir Verchand, Ashwin Pananjady. Mathematical Programming Ser. B, Sep 2025.
- Computationally efficient reductions between some statistical models, Mengqi Lou, Guy Bresler, Ashwin Pananjady. IEEE Transactions on Information Theory, Sep 2025.
- Just Wing It: Near-optimal estimation of missing mass in a Markovian sequence, Ashwin Pananjady, Vidya Muthukumar, Andrew Thangaraj. Journal of Machine Learning Research, Oct 2024.
- Accelerated and instance-optimal policy evaluation with linear function approximation, Tianjiao Li, Guanghui Lan, Ashwin Pananjady. SIAM Journal on Mathematics of Data Science (SIMODS), Mar 2023.
- Sharp global convergence guarantees for iterative nonconvex optimization with random data, Kabir Chandrasekher, Ashwin Pananjady, Christos Thrampoulidis. Annals of Statistics, Feb 2023.