6 papers
Fundamental Limits for Sensor-Based Control via the Gibbs Variational Principle
Vincent Pacelli, Evangelos A. Theodorou
Fundamental limits on the performance of feedback controllers are essential for benchmarking algorithms, guiding sensor selection, and certifying task feasibility -- yet few genera…
Variational Inference via Entropic Transport Descent
Vincent Pacelli, Akash Ratheesh, Evangelos Theodorou
Particle-based variational inference (ParVI) methods approximate an intractable target distribution by evolving an ensemble of interacting samples. Existing approaches rely predomi…
Sampling-Based Control via Entropy-Regularized Optimal Transport
Vincent Pacelli, Akash Ratheesh, Evangelos A. Theodorou
Sampling-based model predictive control methods like MPPI and CEM are essential for real-time control of nonlinear robotic systems, particularly where discontinuous dynamics preclu…
Operator Splitting Covariance Steering for Safe Stochastic Nonlinear Control
Akash Ratheesh, Vincent Pacelli, Augustinos D. Saravanos +1
This paper presents a novel algorithm for solving distribution steering problems featuring nonlinear dynamics and chance constraints. Covariance steering (CS) is an emerging method…
Feedback Schrödinger Bridge Matching
Panagiotis Theodoropoulos, Nikolaos Komianos, Vincent Pacelli +2
Recent advancements in diffusion bridges for distribution transport problems have heavily relied on matching frameworks, yet existing methods often face a trade-off between scalabi…
Deep Distributed Optimization for Large-Scale Quadratic Programming
Augustinos D. Saravanos, Hunter Kuperman, Alex Oshin +3
Quadratic programming (QP) forms a crucial foundation in optimization, encompassing a broad spectrum of domains and serving as the basis for more advanced algorithms. Consequently,…