Supervised learning in function spaces is an emerging area of machine learning research with applications to the prediction of complex physical systems such as fluid flows, solid mechanics, and climate modeling.
We consider a linear stochastic bandit problem involving $M$ agents that can collaborate via a central server to minimize regret.
For discrete-time stochastic processes, we show under which conditions the approximate STL robustness risk can even be computed exactly.
Recent years have witnessed a growing interest in the topic of min-max optimization, owing to its relevance in the context of generative adversarial networks (GANs), robust control and optimization, and reinforcement learning.
Then, we employ this benchmark controller to derive a novel robustly stable adaptive SMPC scheme that learns the necessary noise statistics online, while guaranteeing time-uniform satisfaction of the unknown reformulated state constraints with high probability.
Lipschitz constants of neural networks allow for guarantees of robustness in image classification, safety in controller design, and generalizability beyond the training data.
We study the temporal robustness of temporal logic specifications and show how to design temporally robust control laws for time-critical control systems.
Based on this analysis, we show how a generative approach for learning the nuisance transformations can help transfer invariances across classes and improve performance on a set of imbalanced image classification benchmarks.
Specifically, in our setup, an agent interacting with an environment transmits encoded estimates of an unknown model parameter to a server over a communication channel of finite capacity.
From a theoretical point of view, this framework overcomes the trade-offs between the performance and the sample-complexity of worst-case and average-case learning.
Supervised operator learning is an emerging machine learning paradigm with applications to modeling the evolution of spatio-temporal dynamical systems and approximating general black-box relationships between functional data.
We provide a decentralized control law that exponentially stabilizes the motion of the agents and captures Reynolds boids motion for swarms by using GPs as an online learning-based oracle for the prediction of the unknown dynamics.
In particular, we leverage semi-infinite optimization and non-convex duality theory to show that adversarial training is equivalent to a statistical problem over perturbation distributions, which we characterize completely.
Estimating the region of attraction (ROA) of general nonlinear autonomous systems remains a challenging problem and requires a case-by-case analysis.
We propose a Safe Pontryagin Differentiable Programming (Safe PDP) methodology, which establishes a theoretical and algorithmic framework to solve a broad class of safety-critical learning and control tasks -- problems that require the guarantee of safety constraint satisfaction at any stage of the learning and control progress.
We present a robust control framework for time-critical systems in which satisfying real-time constraints robustly is of utmost importance for the safety of the system.
Despite remarkable success in a variety of applications, it is well-known that deep learning can fail catastrophically when presented with out-of-distribution data.
We consider a standard federated learning (FL) architecture where a group of clients periodically coordinate with a central server to train a statistical model.
Contrary to our expectations, linear auto-regressive models achieve the best measures across all three metrics, eliminating the trade-off between accuracy and simplicity.
By designing the learner and the verifier according to the analytic center cutting-plane method from convex optimization, we show that when the set of Lyapunov functions is full-dimensional in the parameter space, our method finds a Lyapunov function in a finite number of steps.
Optimization and Control
Our method can handle an arbitrary number of pursuers and targets; we show results for tasks consisting up to 1000 pursuers tracking 1000 targets.
This paper focuses on the controller synthesis for unknown, nonlinear systems while ensuring safety constraints.
To overcome this issue, we present a tracking control law for underactuated rigid-body dynamics using an online learning-based oracle for the prediction of the unknown dynamics.
In particular, we introduce Active Tracking Target Network (ATTN), a unified RL policy that is capable of solving major sub-tasks of active target tracking -- in-sight tracking, navigation, and exploration.
Deterministic Policy Gradient (DPG) removes a level of randomness from standard randomized-action Policy Gradient (PG), and demonstrates substantial empirical success for tackling complex dynamic problems involving Markov decision processes.
Indeed, natural variation such as lighting or weather conditions can significantly degrade the accuracy of trained neural networks, proving that such natural variation presents a significant challenge for deep learning.
Here we demonstrate that a recurrent neural network (RNN) can learn to modify its representation of complex information using only examples, and we explain the associated learning mechanism with new theory.
By interpreting the min-max problem as an optimal control problem, it has recently been shown that one can exploit the compositional structure of neural networks in the optimization problem to improve the training time significantly.
There has been an increasing interest in using neural networks in closed-loop control systems to improve performance and reduce computational costs for on-line implementation.
We show that when the system identification step produces sufficiently accurate estimates, or when the underlying true KF is sufficiently robust, that a Certainty Equivalent (CE) KF, i. e., one designed using the estimated parameters directly, enjoys provable sub-optimality guarantees.
Despite the simplicity and intuitive interpretation of Minimum Mean Squared Error (MMSE) estimators, their effectiveness in certain scenarios is questionable.
Upon further assuming the use of near-universal policy parameterizations, we also develop explicit bounds on the gap between optimal values of initial, infinite dimensional resource allocation problems, and dual values of their parameterized smoothed surrogates.
In this regard our work is the first to characterize the amount of channel modeling that is required to answer such a question.
In this paper, we propose a novel Reinforcement Learning approach for solving the Active Information Acquisition problem, which requires an agent to choose a sequence of actions in order to acquire information about a process of interest using on-board sensors.
In this context, we discuss two relevant problems: (i) probabilistic safety verification, in which the goal is to find an upper bound on the probability of violating a safety specification; and (ii) confidence ellipsoid estimation, in which given a confidence ellipsoid for the input of the neural network, our goal is to compute a confidence ellipsoid for the output.
Since, DRM overestimates the number of attacks in each clique, in this paper we also introduce an Improved Distributed Robust Maximization (IDRM) algorithm.
Given this distributed setting, we develop Constraint-Distributed Continuous Greedy (CDCG), a message passing algorithm that converges to the tight $(1-1/e)$ approximation factor of the optimum global solution using only local computation and communication.
Reinforcement Learning (RL) has emerged as an efficient method of choice for solving complex sequential decision making problems in automatic control, computer science, economics, and biology.
The resulting SDP can be adapted to increase either the estimation accuracy (by capturing the interaction between activation functions of different layers) or scalability (by decomposition and parallel implementation).
Certifying the safety or robustness of neural networks against input uncertainties and adversarial attacks is an emerging challenge in the area of safe machine learning and control.
In this setting, we first consider a feasibility problem consisting of tuning the edge weights such that certain controllability properties are satisfied.
Optimization and Control
This paper presents Verisig, a hybrid system approach to verifying safety properties of closed-loop systems using neural networks as controllers.
Systems and Control
The development of large-scale distributed control systems has led to the outsourcing of costly computations to cloud-computing platforms, as well as to concerns about privacy of the collected sensitive data.
Optimization and Control Cryptography and Security Systems and Control
The objective of this paper is to focus on resilient matroid-constrained problems arising in control and sensing but in the presence of sensor and actuator failures.
We propose protocols for two cloud-MPC architectures motivated by the current developments in the Internet of Things: a client-server architecture and a two-server architecture.
Optimization and Control Cryptography and Security Systems and Control
In this paper, we provide the first algorithm, enabling the following capabilities: minimal communication, i. e., the algorithm is executed by the robots based only on minimal communication between them; system-wide resiliency, i. e., the algorithm is valid for any number of denial-of-service attacks and failures; and provable approximation performance, i. e., the algorithm ensures for all monotone (and not necessarily submodular) objective functions a solution that is finitely close to the optimal.
In this paper, we provide the first scalable algorithm, that achieves the following characteristics: system-wide resiliency, i. e., the algorithm is valid for any number of denial-of-service attacks, deletions, or failures; adaptiveness, i. e., at each time step, the algorithm selects system elements based on the history of inflicted attacks, deletions, or failures; and provable approximation performance, i. e., the algorithm guarantees for monotone objective functions a solution close to the optimal.
Many accurate and efficient methods exist that address this problem but most assume that the occupancy states of different elements in the map representation are statistically independent.
We formulate an efficient closed-form solution for the value update by approximately estimating analytic parameters of the posterior of the Q-beliefs.
This paper presents an active approach for part-based object detection, which optimizes the order of part filter evaluations and the time at which to stop and make a prediction.
One of the central problems in computer vision is the detection of semantically important objects and the estimation of their pose.