arXiv research

New framework for analyzing games with multi-dimensional singular controls and non-linear jumps.

Solves optimal control with state constraints using probabilistic methods.

Hybrid systems are characterized by having an interaction between continuous dynamics and discrete events. The contribution of this paper is to provide hybrid systems with a novel geometric formulation so that controls can be added. Using this framework we describe some new global controllability tests for hybrid contr…

We consider the problem of controlling a possibly unknown linear dynamical system with adversarial perturbations, adversarially chosen convex loss functions, and partially observed states, known as non-stochastic control. We introduce a controller parametrization based on the denoised observations, and prove that apply…

A new method controls risk for set predictors using cross-validation.

The paper extends conformal risk control to be valid with high probability over a growing calibration dataset.

Non-bilinear observations make optimal control harder, showing non-convex costs and non-affine optimal controllers.

Develops a framework to control risk in online learning models.

Traditional control methods are inadequate in many deployment settings involving control of Cyber-Physical Systems (CPS). In such settings, CPS controllers must operate and respond to unpredictable interactions, conditions, or failure modes. Dealing with such unpredictability requires the use of executive and cognitive…

New methods control false discoveries near the boundary in conformal novelty detection.

Agents acting in the natural world aim at selecting appropriate actions based on noisy and partial sensory observations. Many behaviors leading to decision mak- ing and action selection in a closed loop setting are naturally phrased within a control theoretic framework. Within the framework of optimal Control Theory, o…

We study the question of how to aggregate controllers for dynamical systems in order to improve their performance. To this end, we propose a framework of boosting for online control. Our main result is an efficient boosting algorithm that combines weak controllers into a provably more accurate one. Empirical evaluation…

New methods prove controllability of non-linear systems, extending classical results.

Study optimal control in unknown nonlinear systems with near-optimal regret bound.

New algorithm minimizes worst-case regret in uncertain, time-varying dynamics.

New algorithm solves mean-field control problems using actor-critic learning with moment neural networks.

The paper offers a method to create prediction sets with uncertainty control.

Polynomial-time reachability for LTI systems with TLL NN controllers is achieved.

Develops methods to select informative conformal prediction sets with FCR control.

Performing controlled experiments on noisy data is essential in understanding deep learning across noise levels. Due to the lack of suitable datasets, previous research has only examined deep learning on controlled synthetic label noise, and real-world label noise has never been studied in a controlled setting. This pa…

Efficiently controls unknown linear systems with black-box interactions.

A new method solves complex control problems with random coefficients.

Biological research often involves testing a growing number of null hypotheses as new data is accumulated over time. We study the problem of online control of the familywise error rate (FWER), that is testing an apriori unbounded sequence of hypotheses (p-values) one by one over time without knowing the future, such th…

New method uses unlabeled data to estimate intercept in case-control logistic regression.

Study of 2D Lorentzian anti-de Sitter plane using geometric control theory.

Machine and reinforcement learning (RL) are increasingly being applied to plan and control the behavior of autonomous systems interacting with the physical world. Examples include self-driving vehicles, distributed sensor networks, and agile robots. However, when machine learning is to be applied in these new settings,…

New method controls renewable energy storage and portfolio selection with probabilistic constraints.

Motivated by the recent applications of game-theoretical learning techniques to the design of distributed control systems, we study a class of control problems that can be formulated as potential games with continuous action sets, and we propose an actor-critic reinforcement learning algorithm that provably converges t…

We consider in this paper the regularity problem for time-optimal trajectories of a single-input control-affine system on a n-dimensional manifold. We prove that, under generic conditions on the drift and the controlled vector field, any control u associated with an optimal trajectory is smooth out of a countable set o…

Counterexample shows state-constrained optimal control problems can have Young measure gaps.

We construct a time-consistent sublinear expectation in the setting of volatility uncertainty. This mapping extends Peng's G-expectation by allowing the range of the volatility uncertainty to be stochastic. Our construction is purely probabilistic and based on an optimal control formulation with path-dependent control …

In a seminal paper Abadie, Diamond, and Hainmueller [2010] (ADH), see also Abadie and Gardeazabal [2003], Abadie et al. [2014], develop the synthetic control procedure for estimating the effect of a treatment, in the presence of a single treated unit and a number of control units, with pre-treatment outcomes observed f…

New method infers causal effects without knowing control variables.

New approach to control diffusion processes with soft constraints.

The paper analyzes deep neural networks using control theory to set a time limit for their convergence.

Combining causality, control, and reinforcement learning for system control.

Iterative method learns unknown constraints for MPC control.

Develops a learning model predictive controller for competitive racing.

Kernel methods identify treatment effects with unobserved confounding using negative controls.

This work presents an explicit-implicit procedure to compute a model predictive control (MPC) law with guarantees on recursive feasibility and asymptotic stability. The approach combines an offline-trained fully-connected neural network with an online primal active set solver. The neural network provides a control inpu…

In this paper we study a new reinforcement learning setting where the environment is non-rewarding, contains several possibly related objects of various controllability, and where an apt agent Bob acts independently, with non-observable intentions. We argue that this setting defines a realistic scenario and we present …

Study nonparametric estimator for Markov chain transition matrices in offline setting.

New Lagrangian approach for optimal control of second-order systems.

New algorithm controls systems with unknown, changing losses.

Deep residual networks can approximate any continuous function using control theory.

We introduce a new algorithm for online linear-quadratic control in a known system subject to adversarial disturbances. Existing regret bounds for this setting scale as $\sqrt{T}$ unless strong stochastic assumptions are imposed on the disturbance process. We give the first algorithm with logarithmic regret for arbitra…

Motivated by vision-based control of autonomous vehicles, we consider the problem of controlling a known linear dynamical system for which partial state information, such as vehicle position, is extracted from complex and nonlinear data, such as a camera image. Our approach is to use a learned perception map that predi…

Control data constructed for smooth weak deformation retraction of stratified spaces.