Ali Jadbabaie

Ali Jadbabaie is the JR East Professor of Engineering and Head of MIT’s Department of Civil and Environmental Engineering. He is a core faculty member of the Institute for Data, Systems, and Society; an investigator in the Laboratory for Information and Decision System; and director of the Sociotechnical Systems Research Center. Jadbabaie’s research interests include network science, network economics, decision theory, consensus and information aggregation in social networks, cooperative control of multi-agent systems, applications of algebraic topology in network science and analysis, optimization, and control of networked dynamical systems in physics, engineering and biology.

Jadbabaie has received an NSF Career Award, an Office of Naval Research Young  Investigator Award  and a Vannevar Bush Faculty Fellowship. He earned a BS in electrical engineering from Sharif University, an MS in electrical engineering from the University of New Mexico, and a PhD in control and dynamical systems from Caltech.

Publications

• Zhang, T. He, S. Sra, and A. Jadbabaie (2020). Why Gradient Clipping Accelerates Training: A Theoretical Justification for Adaptivity. Proceedings of International Conference on Learning Representations (ICLR) (Oral Presentation)
• Reiszadeh, A. Mokhtari, H. Hassani, A. Jadbabaie, R Pedarsani (2020). FedPAQ: A Communication Efficient Federated Learning Method with Periodic Averaging and Quantization. Proceedings of AISTATS
• Yun, S. Sra, A. Jadbabaie. (2019). Small ReLU networks are powerful memorizers: a tight analysis of memorization capacity. Proceedings of NeurIPS, Vancouver, Canada (oral Spotlight)
• Yun, S. Sra, A. Jadbabaie. (2019). Are deep ResNets provably better than linear predictors? Proceedings of NeurIPS, Vancouver, Canada
• Yun, S. Sra, A. Jadbabaie. (2019). Small nonlinearities in activation functions create bad local minima in neural networks. Proceedings of International Conference on Learning Representations (ICLR)
• Yun, S. Sra, A. Jadbabaie. (2019). Efficiently testing local optimality and escaping saddles for ReLU networks. Proceedings of International Conference on Learning Representations (ICLR)
• Hazla, A. Jadbabaie, E. Mossel, and M. A Rahimian. (2020). Bayesian decision making in groups is hard. Operations Research
• HT Wai, S. Segarra, A. Scaglione, A, Ozdaglar, A Jadbabaie. (2020). Blind Community Detection from Low-rank Excitations of a Graph Filter. IEEE Transactions on Signal Processing
• M Schaub, A. Benson, G Lippner, P. Horn, and A. Jadbabaie. (2020). Random Walks on Simplicial Complexes and Hodge Laplacians. SIAM Review
• Ajorlou, A. and Jadbabaie, A. (2020). Local Optimality of Almost Piecewise-Linear Quantizers for Witsenhausen’s Problem. IEEE Transactions on Automatic Control (to appear)
• Molavi, P., Tahbaz-Salehi, A., Jadbabaie, A. (2018). A Theory of Non-Bayesian Social Learning. Econometrica, Vol. 86, No. 2, pp. 445-490

Media

• Oct. 29, 2019. Foreign Policy, Baghdadi’s Martyrdom Bump
• Jul. 10, 2019. MIT News, IDSS hosts inaugural Learning for Dynamics and Control conference.
• Apr. 30, 2019. IDSS News,Team Led by Ali Jadbabaie Receives ARO MURI Award.
• Mar. 12, 2019. MIT News, CEE event showcases multidisciplinary opportunities.
• Nov. 14, 2016. MIT News, Tackling society’s big problems with systems theory.