Professor Navid Azizan, MIT: Reliable AI by Design
Reliable AI by Design
AI models are increasingly being deployed in domains where violating a safety, physical, or structural constraint is not merely undesirable, but unacceptable. Yet most modern learning systems encode such requirements through data or soft penalties, providing little assurance when deployed beyond the training distribution. In this talk, I will discuss recent efforts by my group toward building hard constraints directly into learning-based decision-making systems, while retaining the flexibility and scalability that make modern machine learning effective. I will begin with hard-constrained neural networks (HardNets), which embed differentiable constraint-enforcement mechanisms into existing architectures, enabling end-to-end learning under various constraints while preserving expressivity and guaranteeing feasibility. I will then discuss how HardNets can be used to address important problems in dynamical systems and control, including learning chaotic dynamics with boundedness guarantees via energy-constrained operators, as well as safe yet scalable learning-based control and reinforcement learning. Finally, I will turn to modern generative models, namely diffusion and flow-matching models, where treating sampling as an optimal control problem allows us to impose constraints on the final generated sample without unnecessarily restricting the intermediate sampling dynamics, with applications spanning robotic manipulation and planning, PDE control, and language-guided image editing. Together, these advances pave the way for reliable decision-making systems with intrinsic guarantees.
Related papers:
- HardNet: Hard-Constrained Neural Networks with Universal Approximation Guarantees
- HardNet++: Nonlinear Constraint Enforcement in Neural Networks
- ECO: Energy-Constrained Operator Learning for Chaotic Dynamics with Boundedness Guarantees
- PS2-RL: Provably Safe, Yet Scalable Reinforcement Learning
- HardFlow: Hard-Constrained Sampling for Flow-Matching Models via Trajectory Optimization
- DiRecT: Safe Diffusion-Based Planning via Receding-Horizon Denoising