arXiv subjects

Timm Faulwasser

Publications and source records attributed to Timm Faulwasser.

At least 19 recordsLinked to original sources

arXiv2026

Towards an Optimal Control Foundation of Early Exits - Turnpikes and ResNets

The feed-forward propagation through neural networks is crucial for training and inference. To trade off efficiency and accuracy, it has been proposed to consider intermediate outputs of hidden states as data-dependent regularization during training and, ultimately, as early-exits during inference. In this work, we analyze the joint optimization of loss functions computed for the output layer and intermediate layers using optimal control theory. We prove that ResNets trained in this joint fashion exhibit the so-called turnpike phenomenon, this implies that the number of layers required to reach a prescribed loss level is bounded from above independently of the overall network depth. This induces a similarity property across the internal representations of early-exiting networks of varying depths. We connect the turnpike to the overthinking phenomenon, and provide theoretical insights into the success of early-exit criteria derived from softmax probabilities, specifically entropy and max-probability. In a range of experiments, we demonstrate the existence and effect of turnpikes and the resulting similarity in the early-exit performance for ResNets of varying depths.

cs.LG↗

arXiv2026

Optimal energy conversion -- A port-Hamiltonian approach

This paper studies optimal energy conversion in port-Hamiltonian systems. We analyze state- and control-constrained finite-horizon optimal control problems that maximize energy conversion efficiencies. Under suitable reachability conditions, we show that the asymptotic optimal efficiencies exist and coincide with the corresponding optimal cyclic efficiencies. For a class of port-Hamiltonian systems describing coupled storage-conversion components, we further derive intrinsic limits on achievable energy conversion and establish a generalized Carnot-type efficiency bound. Our results provide an optimal-control framework connecting asymptotic optimal operation, cyclic operation, and fundamental efficiency limits for port-Hamiltonian systems.

eess.SY↗

arXiv2026

Port-Hamiltonian Neural Networks for Systems with Multiple Asymptotically Stable Equilibria

Stable port-Hamiltonian neural networks certify asymptotic stability by construction. Yet, their Hamiltonian is a global Lyapunov function with a single global minimum, so they can represent only dynamic systems with one attractor. We demonstrate that this excludes even simple systems with energy landscapes forming a double well, and we overcome the restriction by parametrising the Hamiltonian as a product of Bregman divergences generated by one input-convex network. We prove that the resulting model is locally Lyapunov stable, that the coexistence of stable equilibria forces additional non-asymptotically-stable equilibria to exist, that all equilibria lie in a bounded region, and under a hyperbolicity assumption that almost-everywhere stability holds. On three systems our approach is able to recover the energy surface characteristics and improve the convergence speed by 1.8$\times$-8.5$\times$.

cs.LG↗

arXiv2026

Receding Horizon Control and Dissipativity - Optimal Control, Games and Uncertainty

We provide a tutorial overview of receding horizon control across deterministic, stochastic, multi-agent, and game-theoretic settings. We contrast the minimizer of an optimal control problem with the equilibrium of a game in terms of cost and constraint handling to motivate the difference of MPC schemes involving multiple agents/players. Interestingly, dissipativity theory and the turnpike property have turned out to be a unifying thread and system-theoretic backbone across all these schemes. This paper is the first to give an overview of results, summarizing fundamental insights, drawing parallels, and highlighting technical differences in dissipativity and turnpike analysis across economic, game theoretic, and stochastic settings. We also explore recent trends in numerical methods for games. We conclude by pointing to a list of open challenges.

eess.SY↗

arXiv2026

Energy-optimal predictive control of discrete-time port-Hamiltonian systems: Closed-loop practical stability

We study a dissipativity-based model predictive control (MPC) scheme for energy-optimal constrained output stabilization of a discrete-time nonlinear SISO port-Hamiltonian system described by difference and differential representation. For the optimal control problem to be solved in each MPC step, we establish a measure turnpike behavior. The turnpike set in our work is obtained from the underlying port-Hamiltonian structure without assuming existence of steady-states or periodic orbits. In particular, unlike existing results which typically establish the turnpike property w.r.t. a controlled forward invariant set such as optimal steady-states or optimal periodic orbits, we do not require the turnpike set to be forward control invariant. For MPC, we establish recursive feasibility and show practical stability to the turnpike set w.r.t. the MPC closed loop leveraging both dissipativity and the port-Hamiltonian structure. Finally, we demonstrate our results using two numerical examples.

eess.SY↗

arXiv2026

Fast Risk Certification of Candidate Trajectories under Uncertain Time-Varying Constraints

This paper studies the certification of a fixed candidate trajectory on a finite certification grid under parametric uncertainty. For each constraint-time pair, we define a scalar measure of constraint violation and aggregate the resulting pointwise chance constraints into a worst-case Value-at-Risk (VaR) margin. The goal is not to generate a new trajectory, but to assess online whether a trajectory produced by a planner or predictive controller is sufficiently safe on the certification grid. Direct evaluation requires repeated uncertainty propagation and is often too expensive for computationally demanding models. We therefore adopt an offline-online scheme: offline, a surrogate of the constraint violation map along the candidate trajectory is constructed using polynomial chaos expansion (PCE) when the uncertainty law is known, or kernel regression when only sampled input-output data are available; online, the surrogate is sampled to evaluate conservative VaR bounds at low computational cost. On the theoretical side, we derive a finite-sample upper bound for the grid-based VaR margin using empirical quantiles, the Dvoretzky-Kiefer-Wolfowitz (DKW) inequality, and a union bound over all constraint-time pairs, without assuming a parametric family for the underlying violation distribution. We also show how a uniform surrogate error bound transfers to the certified VaR margin. The approach is illustrated on a crystallization population balance model, where the surrogate-based risk estimates track direct Monte Carlo results while substantially reducing online evaluation time.

eess.SY↗

arXiv2026

Towards turnpike-based performance analysis of risk-averse stochastic predictive control

In this paper, we present performance estimates for stochastic economic MPC schemes with risk-averse cost formulations. For MPC algorithms with costs given by expectations, it was recently shown that the guaranteed near-optimal performance of abstract MPC in random variables coincides with its implementable variant using pathwise feedback. In general, this property does not extend to costs formulated in terms of risk measures. However, through a turnpike-based analysis, this paper demonstrates that for a particular class of risk measures, this result can still be leveraged to formulate an implementable risk-averse MPC scheme, resulting in near-optimal averaged performance.

math.OC↗

arXiv2026

Stability and performance of stochastic economic MPC -- Stochastic characterization of the closed-loop asymptotics

Model Predictive Control (MPC) is well understood in the deterministic setting, yet rigorous stability and performance guarantees for stochastic MPC remain limited to the consideration of terminal constraints and penalties. In contrast, this work analyzes stochastic economic MPC with an expected cost criterion and establishes closed-loop guarantees without terminal conditions. Relying on stochastic dissipativity and turnpike properties, we construct closed-loop Lyapunov functions that ensure $P$-practical asymptotic stability of a particular optimal stationary process under different notions of stochastic convergence, such as in distribution or in the $p$-th mean. In addition, we derive tight near-optimal bounds for both averaged and non-averaged performance, thereby extending classical deterministic results to the stochastic domain. Finally, we show that the abstract stochastic MPC scheme requiring distributional knowledge shares the same closed-loop properties as a practically implementable algorithm based only on sampled state information, ensuring applicability of our findings. Our findings are illustrated by a numerical example.

math.OC↗

arXiv2026

Uncertainty Propagation under Residual Disturbances: A Smart-Home Case Study

This paper presents a data-driven framework for uncertainty propagation under unmeasured or statistically unmodeled (unstructured) disturbances. We consider residual disturbances, which consolidate all unstructured disturbances into a single quantity that can be estimated from data. Under mild assumptions, the resulting stochastic predictor is causal and distributionally consistent, enabling efficient uncertainty quantification through polynomial chaos expansions and higher-order Chebyshev inequalities. The proposed method is validated using experimental data from a smart home in Norway.

eess.SY↗

arXiv2026

Towards Closed-loop Stability of Nonlinear Receding Horizon Games

We analyze Receding Horizon Games without any MPC-like terminal ingredients. We show that recursive feasibility can be inferred from the turnpike phenomenon under mild assumptions. Moreover, we prove sufficient conditions for practical asymptotic convergence of the closed-loop trajectories, and we discuss how the gap towards practical asymptotic stability may be closed. We use numerical examples to show that the closed-loop region of attraction around the steady-state GNE shrinks exponentially with the horizon length, a behavior previously known only for model predictive control. Further, we apply a linear end penalty and demonstrate in numerical simulations that it suppresses the leaving arc and ensures asymptotic convergence to the steady-state GNE.

eess.SY↗

arXiv2026

On Uniform Error Bounds for Kernel Regression under Non-Gaussian Noise

Providing non-conservative uncertainty quantification for function estimates derived from noisy observations remains a fundamental challenge in statistical machine learning, particularly for applications in safety-critical domains. In this work, we propose novel non-asymptotic probabilistic uniform error bounds for kernel-based regression. Compared to related bounds in the literature that are restricted to (conditionally) independent sub-Gaussian noise, our bounds allow to consider a broad class of non-Gaussian distributions, such as sub-Gaussian, bounded, sub-exponential, and variance/moment-bounded noise. Moreover, our results apply to correlated and uncorrelated noise. We compare our proposed error bounds with existing results in terms of the induced uncertainty region and their performance in safe control, demonstrating the tightness of the proposed bounds.

cs.LG↗

arXiv2026

A Stochastic Fundamental Lemma with Reduced Disturbance Data Requirements

Recently, the fundamental lemma by Willems et al. has been extended towards stochastic LTI systems subject to process disturbances. Using this lemma requires previously recorded data of inputs, outputs, and disturbances. In this paper, we exploit causality concepts of stochastic control to propose a variant of the stochastic fundamental lemma that does not require past disturbance data in the Hankel matrices. Our developments rely on polynomial chaos expansions and on the knowledge of the disturbance distribution. Similar to our previous results, the proposed variant of the fundamental lemma allows to predict future input-output trajectories of stochastic LTI systems. We draw upon a numerical example to illustrate the proposed variant in data-driven control context.

eess.SY↗

arXiv2026

PolyOCP.jl -- A Julia Package for Stochastic OCPs and MPC

The consideration of stochastic uncertainty in optimal and predictive control is a well-explored topic. Recently Polynomial Chaos Expansions (PCE) have received considerable attention for problems involving stochastically uncertain system parameters and also for problems with additive stochastic i.i.d. disturbances. While there exist a number of open-source PCE toolboxes, tailored open-source codes for the solution of OCPs involving additive stochastic i.i.d. disturbances in julia are not available. Hence, this paper introduces the toolbox PolyOCP$.$jl which enables to efficiently solve stochastic OCPs for linear systems subject to a large class of disturbance distributions. We explain the main mathematical concepts between the PCE transcription of stochastic OCPs and how they are provided in the toolbox. We draw upon two examples to illustrate the functionalities of PolyOCP$.$jl.

eess.SY↗

arXiv2026

Towards grid-aware multi-period flexibility aggregation - A constrained zonotope approach

Aggregation schemes provide a means to reduce the computational complexity of power system operation by reducing the number of devices that are considered individually. This can be achieved with tools of computational geometry, where the feasible set is projected onto the decision variables of the point of interconnection. Set projection is computationally expensive, especially in the context of multi-period power system operation. This calls for efficiency improvements via structure exploitation of set representations. This paper proposes efficient flexibility aggregation via constrained zonotopes. We evaluate the performance of the proposed method on a 15-bus distribution grid with time-dependent elements for up to 96 timesteps. The results suggest that the presented method significantly improves computation times compared to classic polytope projection approaches.

math.OC↗

arXiv2026

System-Theoretic Analysis of Dynamic Generalized Nash Equilibria -- Turnpikes and Dissipativity

Generalized Nash equilibria are used in multi-agent control applications to model strategic interactions between agents that are coupled in the cost, dynamics, and constraints, and provide the foundations for game-theoretic MPC (Receding Horizon Games). We study properties of finite-horizon dynamic GNE trajectories from a system-theoretic perspective. We show how strict dissipativity generates the turnpike phenomenon in GNE solutions. Moreover, we establish a converse turnpike result, i.e., the implication from turnpike to strict dissipativity. We derive conditions under which the steady-state GNE is the optimal operating point and, using a game value function, we give a local characterization of the geometry of storage functions. Finally, we design linear terminal penalties that ensure dynamic GNE trajectories applied in open-loop converge to and remain at the steady-state GNE. These connections provide the foundation for future system-theoretic analysis of GNEs similar to those existing in optimal control as well as for recursive feasibility and closed-loop stability results of game-theoretic MPC.

eess.SY↗

arXiv2026

Closed-loop analysis of linear stochastic MPC with risk-averse constraints

Chance constraints are widely used in stochastic model predictive control (MPC) to enforce probabilistic state and input constraints in the presence of unbounded disturbances. However, they only restrict violation probabilities and do not account for the magnitude of rare but severe constraint violations. In this paper, we extend the indirect feedback approach for linear stochastic MPC from chance constraints to risk-averse constraints like the conditional value-at-risk. For the resulting risk-averse MPC scheme, we establish recursive feasibility and closed-loop constraint satisfaction. Furthermore, based on a stochastic dissipativity notion and suitable conditions on the terminal ingredients we show that (near)-optimality of the averaged closed-loop performance can be ensured.

math.OC↗

arXiv2026

Data-Driven Power Flow for Radial Distribution Networks with Sparse Real-Time Data

Real-time control of distribution networks requires accurate information about the system state. In practice, however, such information is difficult to obtain because real-time measurements are available only at a limited number of locations. This paper proposes a novel data-driven power flow (DDPF) framework for balanced radial distribution networks. The proposed algorithm combines the behavioral approach with the DistFlow model and leverages offline historical data to solve power flow problems using only a limited set of real-time measurements. To design DDPF under sparse measurement conditions, we develop a sensor placement problem based on optimal network reductions. This allows us to determine sensor locations subject to a predefined sensor budget and to explicitly account for the radial nature of distribution networks. Unlike approaches that rely on full observability, the proposed framework is designed for practical distribution grids with sparse measurement availability. This enables data-driven power flow for real-time operation while reducing the number of required sensors. On several test cases, the proposed DDPF algorithm could demonstrate accurate voltage magnitude predictions, with a maximum error less than 0.001 p.u., with as little as 25% of total locations equipped with sensors.

eess.SY↗

arXiv2026

Towards Polynomial Immersion of Port-Hamiltonian Systems

Port-Hamiltonian (pH) systems offer a highly structured and energy-based modular framework for control systems. Many pH systems exhibit non-polynomial non-linearities. We consider the problem of immersing such systems into a higher-dimensional polynomial representation. We prove that, along system trajectories, important features of the non-polynomial pH system are preserved such as the internal interconnection geometry, the energy balance relation with passivity supply rate, as well as energy dissipation. We illustrate how the lifted system enables the design of stabilizing feedback laws by combining sum-of-squares optimization with concepts from passivity-based control. We draw upon several examples to illustrate our findings.

eess.SY↗