Navid Azizan Ruhi

Navid Azizan Esther & Harold E. Edgerton Career Development Assistant Professor Massachusetts Institute of Technology (MIT) Email: [last name]@mit.edu

Bio

Navid Azizan is the Esther & Harold E. Edgerton Career Development Assistant Professor at MIT, where he is a Principal Investigator in the Laboratory for Information & Decision Systems (LIDS) and holds dual appointments in the Department of Mechanical Engineering (Control, Instrumentation, & Robotics) and the Schwarzman College of Computing's Institute for Data, Systems, & Society (IDSS). He is also a Core Member of the MIT Statistics and Data Science Center and the Center for Computational Science and Engineering. His research interests broadly lie in machine learning, mathematical optimization, systems and control, and network science. His research lab focuses on various aspects of enabling large-scale intelligent systems, with an emphasis on principled learning and optimization algorithms, with applications in autonomous systems and societal networks. He obtained his PhD in Computing and Mathematical Sciences (CMS) from the California Institute of Technology (Caltech) in 2020, his MSc in electrical engineering from the University of Southern California in 2015, and his BSc in electrical engineering with a minor in physics from Sharif University of Technology in 2013. Prior to joining MIT, he completed a postdoc in the Autonomous Systems Laboratory (ASL) at Stanford University from December 2020 to August 2021. Additionally, he was a research scientist intern at Google DeepMind in 2019. His work has been recognized by several awards, including the 2020 Information Theory and Applications (ITA) Gold Graduation Award and the 2016 ACM GreenMetrics Best Student Paper Award. He was named an Amazon Fellow in Artificial Intelligence in 2017 and a PIMCO Fellow in Data Science in 2018. He was also the first-place winner and a gold medalist at the 2008 National Physics Olympiad in Iran.

Research Interests

• Machine Learning

• Mathematical Optimization

• Systems and Control

• Network Science

Education

• Ph.D. in Computing and Mathematical Sciences
  California Institute of Technology (Caltech)
  Dissertation Title: Large-Scale Intelligent Systems: From Network Dynamics to Optimization Algorithms
  Advisors: Babak Hassibi and Adam Wierman
  Jun 2015 – Aug 2020

• M.Sc. in Electrical Engineering
  University of Southern California
  Aug 2013 – May 2015

• B.Sc. in Electrical Engineering with Minor in Physics
  Sharif University of Technology
  Sep 2009 – Jul 2013

Employment

Massachusetts Institute of Technology Esther & Harold E. Edgerton Career Development Chair, Jul 2022 – Present Assistant Professor, Jul 2021 – Present Affiliations: Laboratory for Information & Decision Systems (LIDS) Department of Mechanical Engineering: Control, Instrumentation, & Robotics (CIR) Schwarzman College of Computing's Institute for Data, Systems, & Society (IDSS) Statistics and Data Science Center (SDSC) and Center for Computational Science and Engineering (CCSE)

Stanford University Postdoctoral Fellow, Dec 2020 – Aug 2021 Autonomous Systems Laboratory (ASL)

California Institute of Technology Graduate Research/Teaching Assistant, Jun 2015 – Aug 2020 Department of Computing and Mathematical Sciences (CMS)

Google DeepMind Research Scientist Intern, Jun 2019 – Oct 2019

Representative Publications

Deep Learning and Autonomy

• Adaptive-Control-Oriented Meta-Learning for Nonlinear Systems
  Robotics: Science and Systems (RSS), 2021

• Sketching Curvature for Efficient Out-of-Distribution Detection for Deep Neural Networks
  Uncertainty in Artificial Intelligence (UAI), 2021
  Selected for full oral presentation

• Orthogonal Gradient Descent for Continual Learning
  International Conference on Artificial Intelligence and Statistics (AISTATS), 2020

Foundations of Deep Learning

• Beyond Implicit Regularization: Avoiding Overfitting via Regularizer Mirror Descent
  International Conference on Machine Learning (ICML) Overparameterization Workshop, 2021
  Selected for spotlight presentation

• Stochastic Mirror Descent on Overparameterized Nonlinear Models
  IEEE Transactions on Neural Networks and Learning Systems, 2021
  International Conference on Machine Learning (ICML) Generalization Workshop, 2019

• Stochastic Gradient/Mirror Descent: Minimax Optimality and Implicit Regularization
  International Conference on Learning Representations (ICLR), 2019
  Neural Information Processing Systems (NeurIPS) Deep Learning Theory Workshop, 2018
  Winner of the ITA Graduation-Day Gold Award, 2020

Markets for the Smart Grid

• Optimal Pricing in Markets with Non-Convex Costs
  Operations Research (OR), 2020
  Proceedings of the ACM Conference on Economics and Computation (EC), 2019

• Opportunities for Price Manipulation by Aggregators in Electricity Markets
  IEEE Transactions on Smart Grid (TSG), 2017
  ACM Performance Evaluation Review (PER), 2016
  Winner of the ACM GREENMETRICS Best Student Paper Award, 2016

Algorithms for Distributed Computation

• Distributed Solution of Large-Scale Linear Systems via Accelerated Projection-Based Consensus
  IEEE Transactions on Signal Processing (TSP), 2019
  Winner of the Amazon Fellowship, 2017

• Improving Distributed Gradient Descent Using Reed-Solomon Codes
  Submitted to the IEEE Transactions on Information Theory
  Proceedings of the IEEE International Symposium on Information Theory (ISIT), 2018

Spreading Processes in Complex Networks

• Improved Bounds on the Epidemic Threshold of Exact SIS Models on Complex Networks
  Proceedings of the IEEE Conference on Decision and Control (CDC), 2016
  Invited Paper

• SIRS Epidemics on Complex Networks: Concurrence of Exact Markov Chain and Approximated Models
  Proceedings of the IEEE Conference on Decision and Control (CDC), 2015
  Invited Paper

[Full list of publications]