Navid Azizan
Massachusetts Institute of Technology (MIT)
Seminar Information
As machine learning models continue to deliver impressive results, the excitement around deploying them in real-world systems grows. However, the reliable deployment of these models in safety-critical systems is hindered by several factors, such as their unpredictable behavior on data points significantly different from their training sets, their inability to incorporate hard constraints, and their data-hungry nature. This talk presents recent advances in enhancing the safety and reliability of machine learning models. First, I will introduce a framework for incorporating hard constraints into the training pipelines of deep neural networks without compromising their expressivity, achieved through a differentiable projection layer that enforces constraints by construction while allowing unconstrained optimization of network parameters. Second, I will discuss run-time monitors for machine learning models, focusing on uncertainty estimation and out-of-distribution detection mechanisms for pre-trained models and latent representations, which mitigate risks associated with unforeseen operational deviations. Lastly, I will present control-oriented meta-learning and continual learning methods that enable fast, efficient, on-the-fly model adaptation from newly collected, limited data in dynamic environments. Together, these advances pave the way for safe and efficient data-driven control and decision-making systems with intrinsic safety and stability guarantees.
Related papers:
- HardNet: Hard-Constrained Neural Networks with Universal Approximation Guarantees
- Data-Driven Control with Inherent Lyapunov Stability
- HardFlow: Hard-Constrained Sampling for Flow-Matching Models via Trajectory Optimization
- Safe Multi-Agent Reinforcement Learning with Convergence to Generalized Nash Equilibrium
- Know What You Don't Know: Uncertainty Calibration of Process Reward Models
- ATOM-CBF: Adaptive Safe Perception-Based Control under Out-of-Distribution Measurements
- Meta-Learning for Adaptive Control with Automated Mirror Descent
- ORFit: One-Pass Learning via Bridging Orthogonal Gradient Descent and Recursive Least-Squares
Navid Azizan is the Alfred H. (1929) and Jean M. Hayes Assistant Professor at MIT, where he holds dual appointments in the Department of Mechanical Engineering (Control, Instrumentation & Robotics) and the Institute for Data, Systems & Society (IDSS) and is a Principal Investigator in the Laboratory for Information & Decision Systems (LIDS). Previously, he held the Esther and Harold E. Edgerton (1927) Chair. His research interests broadly lie in machine learning, systems and control, mathematical optimization, and network science. His research lab focuses on various aspects of reliable intelligent systems, with an emphasis on principled learning and optimization algorithms, with applications to autonomy and sociotechnical systems. 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 at Stanford University in 2021. Additionally, he was a research scientist intern at Google DeepMind in 2019. His work has been recognized by several awards, including Research Awards from Google, Amazon, MathWorks, and IBM, and Best Paper awards and nominations at several venues, including ACM Greenmetrics, the Learning for Dynamics & Control (L4DC), and INFORMS JFIG. He was named in the list of Outstanding Academic Leaders in Data by the CDO Magazine for two consecutive years in 2024 and 2023, received the 2020 Information Theory and Applications (ITA) “Sun” (Gold) Graduation Award, and was named an Amazon Fellow in AI in 2017 and a PIMCO Fellow in Data Science in 2018. His mentorship has been recognized with the Frank E. Perkins Award for Excellence in Graduate Advising (MIT Institute Award) in 2025 and the UROP Outstanding Mentor Award in 2023. Early in his academic journey, he was the first-place winner and a gold medalist at the 2008 National Physics Olympiad in Iran. He founded and co-organized the popular “Control Meets Learning” Virtual Seminar Series during the pandemic.