Search Results for author:
Found 14 papers, 6 papers with code
Common pitfalls to avoid while using multiobjective optimization in machine learning
We highlight the most common pitfalls one should avoid while using MOO techniques in ML.
Predicting PDEs Fast and Efficiently with Equivariant Extreme Learning Machines
We utilize extreme learning machines for the prediction of partial differential equations (PDEs).
On the continuity and smoothness of the value function in reinforcement learning and optimal control
The value function plays a crucial role as a measure for the cumulative future reward an agent receives in both reinforcement learning and optimal control.
A multiobjective continuation method to compute the regularization path of deep neural networks
To overcome this limitation, we present an algorithm that allows for the approximation of the entire Pareto front for the above-mentioned objectives in a very efficient manner for high-dimensional DNNs with millions of parameters.
Partial observations, coarse graining and equivariance in Koopman operator theory for large-scale dynamical systems
The Koopman operator has become an essential tool for data-driven analysis, prediction and control of complex systems, the main reason being the enormous potential of identifying linear function space representations of nonlinear dynamics from measurements.
Learning a model is paramount for sample efficiency in reinforcement learning control of PDEs
The goal of this paper is to make a strong point for the usage of dynamical models when using reinforcement learning (RL) for feedback control of dynamical systems governed by partial differential equations (PDEs).
Distributed Control of Partial Differential Equations Using Convolutional Reinforcement Learning
We present a convolutional framework which significantly reduces the complexity and thus, the computational effort for distributed reinforcement learning control of dynamical systems governed by partial differential equations (PDEs).
Learning Bilinear Models of Actuated Koopman Generators from Partially-Observed Trajectories
Data-driven models for nonlinear dynamical systems based on approximating the underlying Koopman operator or generator have proven to be successful tools for forecasting, feature learning, state estimation, and control.
Efficient time stepping for numerical integration using reinforcement learning
While the classical schemes apply very generally and are highly efficient on regular systems, they can behave sub-optimal when an inefficient step rejection mechanism is triggered by structurally complex systems such as chaotic systems.
On the Universal Transformation of Data-Driven Models to Control Systems
In other words, surrogate modeling for autonomous systems is much easier than for control systems.
On the Treatment of Optimization Problems with L1 Penalty Terms via Multiobjective Continuation
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).
Data-driven approximation of the Koopman generator: Model reduction, system identification, and control
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).
Deep Model Predictive Control with Online Learning for Complex Physical Systems
The control of complex systems is of critical importance in many branches of science, engineering, and industry.
Analyzing high-dimensional time-series data using kernel transfer operator eigenfunctions
Kernel transfer operators, which can be regarded as approximations of transfer operators such as the Perron-Frobenius or Koopman operator in reproducing kernel Hilbert spaces, are defined in terms of covariance and cross-covariance operators and have been shown to be closely related to the conditional mean embedding framework developed by the machine learning community.
