19 citations · 27 across the 16 of their papers we have counts for
19 papers
The Price of Distributional Robustness in Linear Quadratic Control
Andrea Martin, Giuseppe Belgioioso
Distributionally robust (DR) optimization seeks decisions that perform best under the most adverse law within a given ambiguity set, enabling the design of data-driven controllers…
Finite-sample guarantees for data-driven operator splitting methods via martingale inequalities
Andrea Martin, Filippo Fabiani, Giuseppe Belgioioso
Operator splitting methods are a fundamental class of algorithms for solving structured monotone inclusion problems arising in optimization, control, and game theory. We consider t…
Sinkhorn Ambiguity Sets for Distributionally Robust Control: Convexity, Weak Compactness, and Tractability
Riccardo Cescon, Andrea Martin, Giancarlo Ferrari-Trecate
Classical stochastic control assumes perfect knowledge of the uncertainty affecting the plant. In practice, however, such information is often incomplete. To address this limitatio…
Learning to accelerate Krasnosel'skii-Mann fixed-point iterations with guarantees
Andrea Martin, Giuseppe Belgioioso
We introduce a principled learning to optimize (L2O) framework for solving fixed-point problems involving general nonexpansive mappings. Our idea is to deliberately inject summable…
A graph-informed regret metric for optimal distributed control
Daniele Martinelli, Andrea Martin, Giancarlo Ferrari-Trecate +1
We consider the optimal control of large-scale systems using distributed controllers whose network topology mirrors the coupling graph between subsystems. In this work, we introduc…
On the Global Optimality of Linear Policies for Sinkhorn Distributionally Robust Linear Quadratic Control
Riccardo Cescon, Andrea Martin, Giancarlo Ferrari-Trecate
The Linear Quadratic Gaussian (LQG) regulator is a cornerstone of optimal control theory, yet its performance can degrade significantly when the noise distributions deviate from th…
Learning to optimize with guarantees: a complete characterization of linearly convergent algorithms
Andrea Martin, Ian R. Manchester, Luca Furieri
The design of many classical optimization algorithms is driven by the certification of linear convergence rates over classes of optimization problems. In this paper, we consider th…
MAD: A Magnitude And Direction Policy Parametrization for Stability Constrained Reinforcement Learning
Luca Furieri, Sucheth Shenoy, Danilo Saccani +2
We introduce magnitude and direction (MAD) policies, a policy parameterization for reinforcement learning (RL) that preserves Lp closed-loop stability for nonlinear dynamical syste…
Data-driven Distributionally Robust Control Based on Sinkhorn Ambiguity Sets
Riccardo Cescon, Andrea Martin, Giancarlo Ferrari-Trecate
As the complexity of modern control systems increases, it becomes challenging to derive an accurate model of the uncertainty that affects their dynamics. Wasserstein Distributional…
Learning to optimize with convergence guarantees using nonlinear system theory
Andrea Martin, Luca Furieri
The increasing reliance on numerical methods for controlling dynamical systems and training machine learning models underscores the need to devise algorithms that dependably and ef…
Distributionally Robust Infinite-horizon Control: from a pool of samples to the design of dependable controllers
Jean-Sébastien Brouillon, Andrea Martin, John Lygeros +2
We study control of constrained linear systems with only partial statistical information about the uncertainty affecting the system dynamics and the sensor measurements. Specifical…
Closing the Gap to Quadratic Invariance: a Regret Minimization Approach to Optimal Distributed Control
Daniele Martinelli, Andrea Martin, Giancarlo Ferrari-Trecate +1
In this work, we focus on the design of optimal controllers that must comply with an information structure. State-of-the-art approaches do so based on the H2 or Hinfty norm to mini…
On the Guarantees of Minimizing Regret in Receding Horizon
Andrea Martin, Luca Furieri, Florian Dörfler +2
Towards bridging classical optimal control and online learning, regret minimization has recently been proposed as a control design criterion. This competitive paradigm penalizes th…
Regret Optimal Control for Uncertain Stochastic Systems
Andrea Martin, Luca Furieri, Florian Dörfler +2
We consider control of uncertain linear time-varying stochastic systems from the perspective of regret minimization. Specifically, we focus on the problem of designing a feedback c…
Follow the Clairvoyant: an Imitation Learning Approach to Optimal Control
Andrea Martin, Luca Furieri, Florian Dörfler +2
We consider control of dynamical systems through the lens of competitive analysis. Most prior work in this area focuses on minimizing regret, that is, the loss relative to an ideal…
Safe Control with Minimal Regret
Andrea Martin, Luca Furieri, Florian Dörfler +2
As we move towards safety-critical cyber-physical systems that operate in non-stationary and uncertain environments, it becomes crucial to close the gap between classical optimal c…
Near-Optimal Design of Safe Output Feedback Controllers from Noisy Data
Luca Furieri, Baiwei Guo, Andrea Martin +1
As we transition towards the deployment of data-driven controllers for black-box cyberphysical systems, complying with hard safety constraints becomes a primary concern. Two key as…
A Behavioral Input-Output Parametrization of Control Policies with Suboptimality Guarantees
Luca Furieri, Baiwei Guo, Andrea Martin +1
Recent work in data-driven control has revived behavioral theory to perform a variety of complex control tasks, by directly plugging libraries of past input-output trajectories int…
Out-Of-Bag Anomaly Detection
Egor Klevak, Sangdi Lin, Andy Martin +2
Data anomalies are ubiquitous in real world datasets, and can have an adverse impact on machine learning (ML) systems, such as automated home valuation. Detecting anomalies could m…