Unified control theory and machine learning for safety in uncertain systems.
problem Safety guarantees for systems with measurement model uncertainty.
method Measurement-Robust Control Barrier Functions (MR-CBFs) for control synthesis.
result MR-CBFs ensure safety in perception systems with measurement model uncertainty.
New conditions prevent gaps in optimal control problems.
problem Preventing gaps in optimal control problems with state constraints.
method Developed new sufficient conditions not relying on convexity.
result Derived bounds for the size of the relaxation gap.
Study uses viscosity solutions to solve control problems involving measure-valued martingales.
problem Stochastic control problems with measure-valued martingale state processes.
method Viscosity solution approach exploiting structural properties of MVM processes.
result Value function is the unique viscosity solution to the HJB equation.
A new approach models exploration in continuous-time RL using random measures.
problem Modeling exploration in continuous-time reinforcement learning.
method Random measure approach to control execution in continuous-time RL.
result Grid-sampling limit SDE can replace existing models for theoretical analysis and learning algorithms.
Counterexample shows state-constrained optimal control problems can have Young measure gaps.
problem Existence of Young measure gaps in state-constrained optimal control problems.
method Provided a counterexample for smooth controllable systems state-constrained to the unit ball.
result Gap occurs in a regular setting with non-convex Lagrangian density.
New control methods improve dynamic measure transport paths.
problem Improving paths for dynamic measure transport.
method Connecting mean-field games to optimization problems for learning paths, advocating for smoothness of velocities.
result Our method recovers more efficient and smooth transport models compared to untilted paths.
For controlled discrete-time stochastic processes we introduce a new class of dynamic risk measures, which we call process-based. Their main features are that they measure risk of processes that are functions of the history of a base process. We introduce a new concept of conditional stochastic time consistency and we …
Survey explores geometric aspects of policy optimization in control systems.
problem Understanding the geometric relationships between control design and optimization.
method Geometric perspective on policy optimization, focusing on parameterization and topology.
result Implications of policy geometry on stability and performance of local search algorithms.
We give a singular control approach to the problem of minimizing an energy functional for measures with given total mass on a compact real interval, when energy is defined in terms of a completely monotone kernel. This problem occurs both in potential theory and when looking for optimal financial order execution strate…
We solve a complex Bayesian control problem with novel methods.
problem Optimizing control of a hidden signal's influence on noisy observations.
method Measure-valued HJB perspective, viscosity theory, approximation arguments.
result Equivalence to HJB equation and continuous viscosity solution.
Proposes variance reduction techniques for sliced Wasserstein distance estimation.
problem Intractability of estimating sliced Wasserstein distances.
method Uses control variates based on Gaussian approximations of projected measures.
result Significant reduction in variance of SW distance estimators.
Majorizing measures control sequential complexities for online learning.
problem Extending classical empirical processes theory to sequential cases.
method Generic chaining, majorizing measures, fractional covering numbers.
result Sharp control of worst-case sequential Rademacher complexity.
In this paper we consider (x,u)-flat nonlinear control systems with two inputs, and show that every such system can be rendered static feedback linearizable by prolongations of a suitably chosen control. This result is not only of theoretical interest, but has also important implications on the design of flatness bas…
Paper solves tracking control for (x,u)-flat systems using classical states.
problem Tracking control for (x,u)-flat systems. method Quasi-static feedback of classical states.
result Achieves linear, decoupled and asymptotically stable tracking error dynamics.
The paper proposes a new framework for accurate uncertainty representation and propagation.
problem Inaccurate representation and propagation of uncertainty in measurement systems.
method The paper introduces a comprehensive framework using Gaussian Mixture Models (GMMs) for representing and propagating quantitative attributes in measurement systems.
result GMMs offer improved accuracy in representing and propagating measurement uncertainty compared to traditional Gaussian methods, while maintaining computational tractability.
Framework for robust control under model uncertainty, improving financial derivatives hedging.
problem Model uncertainty in financial derivatives hedging.
method Dynamic programming principle for solving one-step optimization problems.
result Robust hedging strategy outperforms model-based strategies during adverse scenarios.
We use martingale and stochastic analysis techniques to study a continuous-time optimal stopping problem, in which the decision maker uses a dynamic convex risk measure to evaluate future rewards. We also find a saddle point for an equivalent zero-sum game of control and stopping, between an agent (the "stopper") who c…
New method uses neural networks to solve complex PDEs from optimal control theory.
problem Solving high-dimensional Hamilton-Jacobi-Bellman PDEs.
method Iterative diffusion optimization techniques, focusing on path measures and divergences.
result Favourable properties of log-variance divergence for Monte Carlo estimators.
We develop a technique based on Malliavin-Bismut calculus ideas, for asymptotic expansion of dual control problems arising in connection with exponential indifference valuation of claims, and with minimisation of relative entropy, in incomplete markets. The problems involve optimisation of a functional of Brownian path…
Safe learning in uncertain systems with state measurements and optimization.
problem Safe learning in nonlinear control-affine systems with unknown additive uncertainty.
method Model uncertainty as Gaussian noise, learn mean and covariance, use optimization to adjust control input.
result Guaranteed safety with arbitrarily large probability while learning and control proceed simultaneously.
Investigates risk measures for DC pension decumulation.
problem Develop optimal decumulation strategies for DC plan holders.
method Formulates decumulation as a control problem, studies risk measures (expected shortfall, linear shortfall, probability of shortfall).
result Optimal controls for expected reward and expected shortfall are identical to those for expected reward and linear shortfall.
AntLer anticipates future learning to improve control performance.
problem Improving control performance through online learning is not well understood.
method AntLer uses a probabilistic model to anticipate future learning and optimize control parameters.
result AntLer approximates optimal solutions with high probability.
Study approximates operators on labelled conditional distributions for non-exchangeable systems.
problem Approximating operators on constrained probability measures for non-exchangeable systems.
method Combines cylindrical approximations and DeepONet-type neural architecture for finite-dimensional representations.
result Establishes a universal approximation theorem for continuous operators on Mλ. New algorithms sample from complex path measures using neural networks.
problem Sampling from posterior path measures under a general prior process.
method Combines controlled equilibrium dynamics and optimization in infinite-dimensional probability space.
result The algorithms can be integrated with neural networks for learning target trajectory ensembles.
Introduces an artificial cyber lab to test and identify cyber resilience measures.
problem Systemic cyber risks and their control methods.
method Classical contagion models and artificial cyber lab simulations.
result Identified two classes of measures: security- and topology-based interventions.
Method predicts hardware resource usage by control software with guaranteed linear convergence.
problem Predicting time-varying hardware resource availability in control software.
method Path structured multimarginal Schrödinger bridge (MSBP) for learning stochastic resource usage.
result Guaranteed linear convergence to accurate prediction of hardware resource utilization.
Complexity measures for neural nets with general activations using path-based norms.
problem Control complexity of neural networks with arbitrary activation functions.
method Approximate general activations with ReLU networks and derive path-based norms for complexity control.
result Preliminary analyses of function spaces and regularized estimators.
Investment strategy optimizes risk using a specific risk measure.
problem Optimizing investment with risk controlled by a weighted entropic risk measure.
method Investigation of expected utility maximization and risk minimization problems with solutions provided iteratively.
result Explicit characterization of solutions to optimization problems.
New measure EC assesses node contributions in nonlinear, time-varying systems.
problem Existing node contribution measures assume linear, time-invariant dynamics, failing for complex, real-world systems.
method Defined 'emergent contribution (EC)' as a dynamical leverage measure from Jacobians of differentiable models.
result EC diverges from average controllability under persistent regime switching and sign reversal, identifying limits of local linearization.
New algorithm learns linear dynamical systems from measurements.
problem Learning system dynamics from linear measurements efficiently and accurately.
method Method of moments estimator to directly estimate Markov parameters.
result First polynomial time algorithm for learning linear dynamical systems.
A new method using spherical harmonics approximates the Sliced-Wasserstein distance.
problem Approximating the Sliced-Wasserstein distance between probability measures.
method Spherical Harmonics Control Variates (SHCV) method for Monte Carlo approximation of the SW distance.
result SHCV method provides an improved rate of convergence compared to Monte Carlo for general measures.
Optimized certainty equivalents (OCEs) is a family of risk measures widely used by both practitioners and academics. This is mostly due to its tractability and the fact that it encompasses important examples, including entropic risk measures and average value at risk. In this work we consider stochastic optimal control…
We describe an abstract control-theoretic framework in which the validity of the dynamic programming principle can be established in continuous time by a verification of a small number of structural properties. As an application we treat several cases of interest, most notably the lower-hedging and utility-maximization…
A new protocol corrects confounding effects to measure alignment-induced activation shifts accurately.
problem Confounding effects in measuring alignment-induced activation shifts using naive methods.
method Introduces a four-variant decomposition to separate alignment shift from template effects.
result Correctly measures alignment-induced activation shifts, recovering behaviorally active subspace.
New measure shows various training techniques control model complexity.
problem Understanding how to control model complexity in deep learning.
method Developed geometric complexity measure and demonstrated its effectiveness.
result Many training techniques control geometric complexity, providing a unified framework.
Deep neural network controllers for autonomous driving have recently benefited from significant performance improvements, and have begun deployment in the real world. Prior to their widespread adoption, safety guarantees are needed on the controller behaviour that properly take account of the uncertainty within the mod…
New conditions ensure MMDs separate and converge to target distributions.
problem Ensuring MMDs separate and converge to target distributions.
method Deriving new sufficient and necessary conditions for MMDs on separable metric spaces.
result First KSDs that exactly metrize weak convergence to P.
New risk measures control subgroup imbalances, improving PAC-Bayesian bounds.
problem Insufficient risk bounds for subgroup imbalances in data.
method Introduce constrained f-entropic risk measures and derive PAC-Bayesian bounds.
result First disintegrated PAC-Bayesian guarantees beyond standard risks.
In this paper, we propose a perturbation framework to measure the robustness of graph properties. Although there are already perturbation methods proposed to tackle this problem, they are limited by the fact that the strength of the perturbation cannot be well controlled. We firstly provide a perturbation framework on …
A framework for robust exploration in reinforcement learning under ambiguity.
problem Optimal stopping under ambiguity in reinforcement learning.
method Continuous-time robust reinforcement learning framework using g-expectation and backward stochastic differential equations. result Constructs a robust exploratory stopping time approximating the optimal stopping time under ambiguity.
This paper is concerned with the problem of stochastic control of gene regulatory networks (GRNs) observed indirectly through noisy measurements and with uncertainty in the intervention inputs. The partial observability of the gene states and uncertainty in the intervention process are accounted for by modeling GRNs us…
Paper proposes method for optimal control of unknown systems with latent states.
problem Jointly estimating dynamics and latent states in systems with unmeasurable states.
method Combination of particle Markov chain Monte Carlo methods and scenario theory.
result Probabilistic performance guarantees for optimal input trajectories.
A PID-based feedback-control system improves multiple KPIs in RTB display advertising.
problem Challenges in simultaneously improving multiple KPIs in RTB campaigns.
method Sequential Control using PID-based feedback and importance metrics.
result Effective in simultaneously controlling multiple KPIs in both simulations and live traffic.
We consider the problem of controlling an unknown linear dynamical system in the presence of (nonstochastic) adversarial perturbations and adversarial convex loss functions. In contrast to classical control, the a priori determination of an optimal controller here is hindered by the latter's dependence on the yet unkno…
New algorithm reduces decision switching in dynamic environments.
problem Online learning with memory and non-stationary environments.
method Dynamic policy regret, novel ensemble approach, meta-base decomposition.
result Proves optimal dynamic policy regret for memory length, non-stationarity, and time horizon.
New measure of interference helps understand and mitigate learning issues in reinforcement learning.
problem Understanding and mitigating interference in reinforcement learning.
method Defined a new measure of interference, evaluated it, and identified key factors contributing to interference.
result Target network frequency and updates on the last layer are significant factors in interference.
We investigate the relationship between measurable differentiable structures on doubling metric measure spaces and derivations. We prove: [1] a decomposition theorem for the module of derivations into free modules; [2] the existence of a measurable differentiable structure assuming that one can control the pointwise up…
This paper examines how data affects risk measures in uncertain distributions.
problem How does distributional ambiguity affect risk measures?
method Formulated and derived simpler dual problems for infinite and finite dimensional robust moment problems.
result Developed theory and conducted experiments in inventory control and portfolio management.