@unpublished{21600,
abstract = {Many problems in science and engineering require the efficient numerical
approximation of integrals, a particularly important application being the
numerical solution of initial value problems for differential equations. For
complex systems, an equidistant discretization is often inadvisable, as it
either results in prohibitively large errors or computational effort. To this
end, adaptive schemes have been developed that rely on error estimators based
on Taylor series expansions. While these estimators a) rely on strong
smoothness assumptions and b) may still result in erroneous steps for complex
systems (and thus require step rejection mechanisms), we here propose a
data-driven time stepping scheme based on machine learning, and more
specifically on reinforcement learning (RL) and meta-learning. First, one or
several (in the case of non-smooth or hybrid systems) base learners are trained
using RL. Then, a meta-learner is trained which (depending on the system state)
selects the base learner that appears to be optimal for the current situation.
Several examples including both smooth and non-smooth problems demonstrate the
superior performance of our approach over state-of-the-art numerical schemes.
The code is available under https://github.com/lueckem/quadrature-ML.},
author = {Dellnitz, Michael and Hüllermeier, Eyke and Lücke, Marvin and Ober-Blöbaum, Sina and Offen, Christian and Peitz, Sebastian and Pfannschmidt, Karlson},
booktitle = {arXiv:2104.03562},
title = {{Efficient time stepping for numerical integration using reinforcement learning}},
year = {2021},
}
@article{16295,
abstract = {It is a challenging task to identify the objectives on which a certain decision was based, in particular if several, potentially conflicting criteria are equally important and a continuous set of optimal compromise decisions exists. This task can be understood as the inverse problem of multiobjective optimization, where the goal is to find the objective function vector of a given Pareto set. To this end, we present a method to construct the objective function vector of an unconstrained multiobjective optimization problem (MOP) such that the Pareto critical set contains a given set of data points with prescribed KKT multipliers. If such an MOP can not be found, then the method instead produces an MOP whose Pareto critical set is at least close to the data points. The key idea is to consider the objective function vector in the multiobjective KKT conditions as variable and then search for the objectives that minimize the Euclidean norm of the resulting system of equations. By expressing the objectives in a finite-dimensional basis, we transform this problem into a homogeneous, linear system of equations that can be solved efficiently. Potential applications of this approach include the identification of objectives (both from clean and noisy data) and the construction of surrogate models for expensive MOPs.},
author = {Gebken, Bennet and Peitz, Sebastian},
journal = {Journal of Global Optimization},
pages = {3--29},
publisher = {Springer},
title = {{Inverse multiobjective optimization: Inferring decision criteria from data}},
doi = {10.1007/s10898-020-00983-z},
volume = {80},
year = {2021},
}
@unpublished{23428,
abstract = {The Koopman operator has become an essential tool for data-driven approximation of dynamical (control) systems in recent years, e.g., via extended dynamic mode decomposition. Despite its popularity, convergence results and, in particular, error bounds are still quite scarce. In this paper, we derive probabilistic bounds for the approximation error and the prediction error depending on the number of training data points; for both ordinary and stochastic differential equations. Moreover, we extend our analysis to nonlinear control-affine systems using either ergodic trajectories or i.i.d.
samples. Here, we exploit the linearity of the Koopman generator to obtain a bilinear system and, thus, circumvent the curse of dimensionality since we do not autonomize the system by augmenting the state by the control inputs. To the
best of our knowledge, this is the first finite-data error analysis in the stochastic and/or control setting. Finally, we demonstrate the effectiveness of the proposed approach by comparing it with state-of-the-art techniques showing its superiority whenever state and control are coupled.},
author = {Nüske, Feliks and Peitz, Sebastian and Philipp, Friedrich and Schaller, Manuel and Worthmann, Karl},
booktitle = {arXiv:2108.07102},
title = {{Finite-data error bounds for Koopman-based prediction and control}},
year = {2021},
}
@unpublished{21199,
abstract = {As in almost every other branch of science, the major advances in data
science and machine learning have also resulted in significant improvements
regarding the modeling and simulation of nonlinear dynamical systems. It is
nowadays possible to make accurate medium to long-term predictions of highly
complex systems such as the weather, the dynamics within a nuclear fusion
reactor, of disease models or the stock market in a very efficient manner. In
many cases, predictive methods are advertised to ultimately be useful for
control, as the control of high-dimensional nonlinear systems is an engineering
grand challenge with huge potential in areas such as clean and efficient energy
production, or the development of advanced medical devices. However, the
question of how to use a predictive model for control is often left unanswered
due to the associated challenges, namely a significantly higher system
complexity, the requirement of much larger data sets and an increased and often
problem-specific modeling effort. To solve these issues, we present a universal
framework (which we call QuaSiModO:
Quantization-Simulation-Modeling-Optimization) to transform arbitrary
predictive models into control systems and use them for feedback control. The
advantages of our approach are a linear increase in data requirements with
respect to the control dimension, performance guarantees that rely exclusively
on the accuracy of the predictive model, and only little prior knowledge
requirements in control theory to solve complex control problems. In particular
the latter point is of key importance to enable a large number of researchers
and practitioners to exploit the ever increasing capabilities of predictive
models for control in a straight-forward and systematic fashion.},
author = {Peitz, Sebastian and Bieker, Katharina},
booktitle = {arXiv:2102.04722},
title = {{On the Universal Transformation of Data-Driven Models to Control Systems}},
year = {2021},
}
@inproceedings{22894,
abstract = {The first order optimality conditions of optimal control problems (OCPs) can
be regarded as boundary value problems for Hamiltonian systems. Variational or
symplectic discretisation methods are classically known for their excellent
long term behaviour. As boundary value problems are posed on intervals of
fixed, moderate length, it is not immediately clear whether methods can profit
from structure preservation in this context. When parameters are present,
solutions can undergo bifurcations, for instance, two solutions can merge and
annihilate one another as parameters are varied. We will show that generic
bifurcations of an OCP are preserved under discretisation when the OCP is
either directly discretised to a discrete OCP (direct method) or translated
into a Hamiltonian boundary value problem using first order necessary
conditions of optimality which is then solved using a symplectic integrator
(indirect method). Moreover, certain bifurcations break when a non-symplectic
scheme is used. The general phenomenon is illustrated on the example of a cut
locus of an ellipsoid.},
author = {Offen, Christian and Ober-Blöbaum, Sina},
keyword = {optimal control, catastrophe theory, bifurcations, variational methods, symplectic integrators},
location = {Berlin, Germany},
title = {{Bifurcation preserving discretisations of optimal control problems}},
year = {2021},
}
@article{16867,
abstract = {In this article, we present an efficient descent method for locally Lipschitz
continuous multiobjective optimization problems (MOPs). The method is realized
by combining a theoretical result regarding the computation of descent
directions for nonsmooth MOPs with a practical method to approximate the
subdifferentials of the objective functions. We show convergence to points
which satisfy a necessary condition for Pareto optimality. Using a set of test
problems, we compare our method to the multiobjective proximal bundle method by
M\"akel\"a. The results indicate that our method is competitive while being
easier to implement. While the number of objective function evaluations is
larger, the overall number of subgradient evaluations is lower. Finally, we
show that our method can be combined with a subdivision algorithm to compute
entire Pareto sets of nonsmooth MOPs.},
author = {Gebken, Bennet and Peitz, Sebastian},
journal = {Journal of Optimization Theory and Applications},
pages = {696--723},
title = {{An efficient descent method for locally Lipschitz multiobjective optimization problems}},
doi = {10.1007/s10957-020-01803-w},
volume = {188},
year = {2021},
}
@article{21195,
author = {Goelz, Christian and Mora, Karin and Stroehlein, Julia Kristin and Haase, Franziska Katharina and Dellnitz, Michael and Reinsberger, Claus and Vieluf, Solveig},
journal = {Cognitive Neurodynamics},
title = {{Electrophysiological signatures of dedifferentiation differ between fit and less fit older adults}},
doi = {10.1007/s11571-020-09656-9},
year = {2021},
}
@article{24170,
author = {Klus, Stefan and Gelß, Patrick and Nüske, Feliks and Noé, Frank},
issn = {2632-2153},
journal = {Machine Learning: Science and Technology},
title = {{Symmetric and antisymmetric kernels for machine learning problems in quantum physics and chemistry}},
doi = {10.1088/2632-2153/ac14ad},
year = {2021},
}
@article{20731,
abstract = {We present a novel algorithm that allows us to gain detailed insight into the effects of sparsity in linear and nonlinear optimization, which is of great importance in many scientific areas such as image and signal processing, medical imaging, compressed sensing, and machine learning (e.g., for the training of neural networks). Sparsity is an important feature to ensure robustness against noisy data, but also to find models that are interpretable and easy to analyze due to the small number of relevant terms. It is common practice to enforce sparsity by adding the ℓ1-norm as a weighted penalty term. In order to gain a better understanding and to allow for an informed model selection, we directly solve the corresponding multiobjective optimization problem (MOP) that arises when we minimize the main objective and the ℓ1-norm simultaneously. As this MOP is in general non-convex for nonlinear objectives, the weighting method will fail to provide all optimal compromises. To avoid this issue, we present a continuation method which is specifically tailored to MOPs with two objective functions one of which is the ℓ1-norm. Our method can be seen as a generalization of well-known homotopy methods for linear regression problems to the nonlinear case. Several numerical examples - including neural network training - demonstrate our theoretical findings and the additional insight that can be gained by this multiobjective approach.},
author = {Bieker, Katharina and Gebken, Bennet and Peitz, Sebastian},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
publisher = {IEEE},
title = {{On the Treatment of Optimization Problems with L1 Penalty Terms via Multiobjective Continuation}},
doi = {10.1109/TPAMI.2021.3114962},
year = {2021},
}
@unpublished{23382,
abstract = {Hamiltonian systems are differential equations which describe systems in classical mechanics, plasma physics, and sampling problems. They exhibit many structural properties, such as a lack of attractors and the presence of conservation laws. To predict Hamiltonian dynamics based on discrete trajectory observations, incorporation of prior knowledge about Hamiltonian structure greatly improves predictions. This is typically done by learning the system's Hamiltonian and then integrating the Hamiltonian vector field with a symplectic integrator. For this, however, Hamiltonian data needs to be approximated based on the trajectory observations. Moreover, the numerical integrator introduces an additional discretisation error. In this paper, we show that an inverse modified Hamiltonian structure adapted to the geometric integrator can be learned directly from observations. A separate approximation step for the Hamiltonian data avoided. The inverse modified data compensates for the discretisation error such that the discretisation error is eliminated. },
author = {Offen, Christian and Ober-Blöbaum, Sina},
title = {{Symplectic integration of learned Hamiltonian systems}},
year = {2021},
}
@article{24169,
author = {Nüske, Feliks and Gelß, Patrick and Klus, Stefan and Clementi, Cecilia},
issn = {0167-2789},
journal = {Physica D: Nonlinear Phenomena},
title = {{Tensor-based computation of metastable and coherent sets}},
doi = {10.1016/j.physd.2021.133018},
year = {2021},
}
@article{16294,
abstract = {Model predictive control is a prominent approach to construct a feedback
control loop for dynamical systems. Due to real-time constraints, the major
challenge in MPC is to solve model-based optimal control problems in a very
short amount of time. For linear-quadratic problems, Bemporad et al. have
proposed an explicit formulation where the underlying optimization problems are
solved a priori in an offline phase. In this article, we present an extension
of this concept in two significant ways. We consider nonlinear problems and -
more importantly - problems with multiple conflicting objective functions. In
the offline phase, we build a library of Pareto optimal solutions from which we
then obtain a valid compromise solution in the online phase according to a
decision maker's preference. Since the standard multi-parametric programming
approach is no longer valid in this situation, we instead use interpolation
between different entries of the library. To reduce the number of problems that
have to be solved in the offline phase, we exploit symmetries in the dynamical
system and the corresponding multiobjective optimal control problem. The
results are verified using two different examples from autonomous driving.},
author = {Ober-Blöbaum, Sina and Peitz, Sebastian},
journal = {International Journal of Robust and Nonlinear Control},
number = {2},
pages = {380--403},
title = {{Explicit multiobjective model predictive control for nonlinear systems with symmetries}},
doi = {10.1002/rnc.5281},
volume = {31},
year = {2021},
}
@unpublished{21572,
author = {Ridderbusch, Steffen and Offen, Christian and Ober-Blöbaum, Sina and Goulart, Paul},
title = {{Learning ODE Models with Qualitative Structure Using Gaussian Processes }},
year = {2021},
}
@article{21337,
abstract = {We present a flexible trust region descend algorithm for unconstrained and
convexly constrained multiobjective optimization problems. It is targeted at
heterogeneous and expensive problems, i.e., problems that have at least one
objective function that is computationally expensive. The method is
derivative-free in the sense that neither need derivative information be
available for the expensive objectives nor are gradients approximated using
repeated function evaluations as is the case in finite-difference methods.
Instead, a multiobjective trust region approach is used that works similarly to
its well-known scalar pendants. Local surrogate models constructed from
evaluation data of the true objective functions are employed to compute
possible descent directions. In contrast to existing multiobjective trust
region algorithms, these surrogates are not polynomial but carefully
constructed radial basis function networks. This has the important advantage
that the number of data points scales linearly with the parameter space
dimension. The local models qualify as fully linear and the corresponding
general scalar framework is adapted for problems with multiple objectives.
Convergence to Pareto critical points is proven and numerical examples
illustrate our findings.},
author = {Berkemeier, Manuel Bastian and Peitz, Sebastian},
issn = {2297-8747},
journal = {Mathematical and Computational Applications},
number = {2},
title = {{Derivative-Free Multiobjective Trust Region Descent Method Using Radial Basis Function Surrogate Models}},
doi = {10.3390/mca26020031},
volume = {26},
year = {2021},
}
@article{21820,
abstract = {The reduction of high-dimensional systems to effective models on a smaller set of variables is an essential task in many areas of science. For stochastic dynamics governed by diffusion processes, a general procedure to find effective equations is the conditioning approach. In this paper, we are interested in the spectrum of the generator of the resulting effective dynamics, and how it compares to the spectrum of the full generator. We prove a new relative error bound in terms of the eigenfunction approximation error for reversible systems. We also present numerical examples indicating that, if Kramers–Moyal (KM) type approximations are used to compute the spectrum of the reduced generator, it seems largely insensitive to the time window used for the KM estimators. We analyze the implications of these observations for systems driven by underdamped Langevin dynamics, and show how meaningful effective dynamics can be defined in this setting.},
author = {Nüske, Feliks and Koltai, Péter and Boninsegna, Lorenzo and Clementi, Cecilia},
issn = {1099-4300},
journal = {Entropy},
title = {{Spectral Properties of Effective Dynamics from Conditional Expectations}},
doi = {10.3390/e23020134},
year = {2021},
}
@article{16961,
author = {Liebendörfer, Michael and Göller, Robin and Biehler, Rolf and Hochmuth, Reinhard and Kortemeyer, Jörg and Ostsieker, Laura and Rode, Jana and Schaper, Niclas},
issn = {0173-5322},
journal = {Journal für Mathematik-Didaktik},
title = {{LimSt – Ein Fragebogen zur Erhebung von Lernstrategien im mathematikhaltigen Studium}},
doi = {10.1007/s13138-020-00167-y},
year = {2020},
}
@article{16290,
abstract = {The control of complex systems is of critical importance in many branches of science, engineering, and industry, many of which are governed by nonlinear partial differential equations. Controlling an unsteady fluid flow is particularly important, as flow control is a key enabler for technologies in energy (e.g., wind, tidal, and combustion), transportation (e.g., planes, trains, and automobiles), security (e.g., tracking airborne contamination), and health (e.g., artificial hearts and artificial respiration). However, the high-dimensional, nonlinear, and multi-scale dynamics make real-time feedback control infeasible. Fortunately, these high- dimensional systems exhibit dominant, low-dimensional patterns of activity that can be exploited for effective control in the sense that knowledge of the entire state of a system is not required. Advances in machine learning have the potential to revolutionize flow control given its ability to extract principled, low-rank feature spaces characterizing such complex systems.We present a novel deep learning modelpredictive control framework that exploits low-rank features of the flow in order to achieve considerable improvements to control performance. Instead of predicting the entire fluid state, we use a recurrent neural network (RNN) to accurately predict the control relevant quantities of the system, which are then embedded into an MPC framework to construct a feedback loop. In order to lower the data requirements and to improve the prediction accuracy and thus the control performance, incoming sensor data are used to update the RNN online. The results are validated using varying fluid flow examples of increasing complexity.},
author = {Bieker, Katharina and Peitz, Sebastian and Brunton, Steven L. and Kutz, J. Nathan and Dellnitz, Michael},
issn = {0935-4964},
journal = {Theoretical and Computational Fluid Dynamics},
pages = {577–591},
title = {{Deep model predictive flow control with limited sensor data and online learning}},
doi = {10.1007/s00162-020-00520-4},
volume = {34},
year = {2020},
}
@unpublished{19941,
abstract = {In backward error analysis, an approximate solution to an equation is
compared to the exact solution to a nearby "modified" equation. In numerical
ordinary differential equations, the two agree up to any power of the step
size. If the differential equation has a geometric property then the modified
equation may share it. In this way, known properties of differential equations
can be applied to the approximation. But for partial differential equations,
the known modified equations are of higher order, limiting applicability of the
theory. Therefore, we study symmetric solutions of discretized partial
differential equations that arise from a discrete variational principle. These
symmetric solutions obey infinite-dimensional functional equations. We show
that these equations admit second-order modified equations which are
Hamiltonian and also possess first-order Lagrangians in modified coordinates.
The modified equation and its associated structures are computed explicitly for
the case of rotating travelling waves in the nonlinear wave equation.},
author = {McLachlan, Robert I and Offen, Christian},
booktitle = {arXiv:2006.14172},
title = {{Backward error analysis for variational discretisations of partial differential equations}},
year = {2020},
}
@article{19939,
author = {Kreusser, Lisa Maria and McLachlan, Robert I and Offen, Christian},
issn = {0951-7715},
journal = {Nonlinearity},
number = {5},
pages = {2335--2363},
title = {{Detection of high codimensional bifurcations in variational PDEs}},
doi = {10.1088/1361-6544/ab7293},
volume = {33},
year = {2020},
}
@article{16288,
abstract = {We derive a data-driven method for the approximation of the Koopman generator called gEDMD, which can be regarded as a straightforward extension of EDMD (extended dynamic mode decomposition). This approach is applicable to deterministic and stochastic dynamical systems. It can be used for computing eigenvalues, eigenfunctions, and modes of the generator and for system identification. In addition to learning the governing equations of deterministic systems, which then reduces to SINDy (sparse identification of nonlinear dynamics), it is possible to identify the drift and diffusion terms of stochastic differential equations from data. Moreover, we apply gEDMD to derive coarse-grained models of high-dimensional systems, and also to determine efficient model predictive control strategies. We highlight relationships with other methods and demonstrate the efficacy of the proposed methods using several guiding examples and prototypical molecular dynamics problems.},
author = {Klus, Stefan and Nüske, Feliks and Peitz, Sebastian and Niemann, Jan-Hendrik and Clementi, Cecilia and Schütte, Christof},
issn = {0167-2789},
journal = {Physica D: Nonlinear Phenomena},
title = {{Data-driven approximation of the Koopman generator: Model reduction, system identification, and control}},
doi = {10.1016/j.physd.2020.132416},
volume = {406},
year = {2020},
}