9 papers
Constrained Flow Matching via Lagrangian Dual Flows
Vince Kurtz, Alexander Davydov
Flow matching is a powerful tool for generative modeling, but emerging applications in robotics, planning, and physics require inference-time constraints on generated outputs. Such…
Regularized Model Predictive Control via Contractivity and Implicit Lur'e Analysis
Ryotaro Shima, Anand Gokhale, Alexander Davydov +1
This paper develops a contraction-based stability analysis for regularized model predictive control (MPC), whose feedback law is defined implicitly by a finite-horizon optimal cont…
Learning Certified Neural Network Controllers Using Contraction and Interval Analysis
Akash Harapanahalli, Samuel Coogan, Alexander Davydov
We present a novel framework that jointly trains a neural network controller and a neural Riemannian metric with rigorous closed-loop contraction guarantees using formal bound prop…
Competition, stability, and functionality in excitatory-inhibitory neural circuits
Simone Betteti, William Retnaraj, Alexander Davydov +2
Energy-based models have become a central paradigm for understanding computation and stability in both theoretical neuroscience and machine learning. However, the energetic framewo…
Non-Euclidean Monotone Operator Theory and Applications
Alexander Davydov, Saber Jafarpour, Anton V. Proskurnikov +1
While monotone operator theory is often studied on Hilbert spaces, many interesting problems in machine learning and optimization arise naturally in finite-dimensional vector space…
Contractivity Analysis and Control Design for Lur'e Systems: Lipschitz, Incrementally Sector Bounded, and Monotone Nonlinearities
Ryotaro Shima, Alexander Davydov, Francesco Bullo
In this paper, we study the contractivity of Lur'e dynamical systems whose nonlinearity is either Lipschitz, incrementally sector bounded, or monotone. We consider both the discret…