Zobrazeno 1 - 10
of 1 226
pro vyhledávání: '"Stellato P"'
Autor:
Sambharya, Rajiv, Stellato, Bartolomeo
We introduce a machine-learning framework to learn the hyperparameter sequence of first-order methods (e.g., the step sizes in gradient descent) to quickly solve parametric convex optimization problems. Our computational architecture amounts to runni
Externí odkaz:
http://arxiv.org/abs/2411.15717
Autor:
Sambharya, Rajiv, Stellato, Bartolomeo
We introduce a data-driven approach to analyze the performance of continuous optimization algorithms using generalization guarantees from statistical learning theory. We study classical and learned optimizers to solve families of parametric optimizat
Externí odkaz:
http://arxiv.org/abs/2404.13831
We consider the problem of designing a machine learning-based model of an unknown dynamical system from a finite number of (state-input)-successor state data points, such that the model obtained is also suitable for optimal control design. We adopt a
Externí odkaz:
http://arxiv.org/abs/2404.01814
This paper introduces a novel data-driven hierarchical control scheme for managing a fleet of nonlinear, capacity-constrained autonomous agents in an iterative environment. We propose a control framework consisting of a high-level dynamic task assign
Externí odkaz:
http://arxiv.org/abs/2403.14545
Autor:
Ranjan, Vinit, Stellato, Bartolomeo
We introduce a numerical framework to verify the finite step convergence of first-order methods for parametric convex quadratic optimization. We formulate the verification problem as a mathematical optimization problem where we maximize a performance
Externí odkaz:
http://arxiv.org/abs/2403.03331
Autor:
Hu, Haimin, Dragotto, Gabriele, Zhang, Zixu, Liang, Kaiqu, Stellato, Bartolomeo, Fisac, Jaime F.
We consider the multi-agent spatial navigation problem of computing the socially optimal order of play, i.e., the sequence in which the agents commit to their decisions, and its associated equilibrium in an N-player Stackelberg trajectory game. We mo
Externí odkaz:
http://arxiv.org/abs/2402.09246
We consider the problem of solving a family of parametric mixed-integer linear optimization problems where some entries in the input data change. We introduce the concept of cutting-plane layer (CPL), i.e., a differentiable cutting-plane generator ma
Externí odkaz:
http://arxiv.org/abs/2311.03350
We introduce the GEneralized Newton Inexact Operator Splitting solver (GeNIOS) for large-scale convex optimization. GeNIOS speeds up ADMM by approximately solving approximate subproblems: it uses a second-order approximation to the most challenging A
Externí odkaz:
http://arxiv.org/abs/2310.08333
We introduce a machine-learning framework to warm-start fixed-point optimization algorithms. Our architecture consists of a neural network mapping problem parameters to warm starts, followed by a predefined number of fixed-point iterations. We propos
Externí odkaz:
http://arxiv.org/abs/2309.07835
We propose a data-driven technique to automatically learn the uncertainty sets in robust optimization. Our method reshapes the uncertainty sets by minimizing the expected performance across a family of problems subject to guaranteeing constraint sati
Externí odkaz:
http://arxiv.org/abs/2305.19225