Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Gramlich, Dennis"'
This paper is devoted to the estimation of the Lipschitz constant of neural networks using semidefinite programming. For this purpose, we interpret neural networks as time-varying dynamical systems, where the $k$-th layer corresponds to the dynamics
Externí odkaz:
http://arxiv.org/abs/2405.01125
We present a simple and effective way to account for non-convex costs and constraints~in~state feedback synthesis, and an interpretation for the variables in which state feedback synthesis is typically convex. We achieve this by deriving the controll
Externí odkaz:
http://arxiv.org/abs/2403.15228
From the perspective of control theory, convolutional layers (of neural networks) are 2-D (or N-D) linear time-invariant dynamical systems. The usual representation of convolutional layers by the convolution kernel corresponds to the representation o
Externí odkaz:
http://arxiv.org/abs/2403.11938
In this work, we develop a method based on robust control techniques to synthesize robust time-varying state-feedback policies for finite, infinite, and receding horizon control problems subject to convex quadratic state and input constraints. To ens
Externí odkaz:
http://arxiv.org/abs/2310.11404
In this paper, we revisit structure exploiting SDP solvers dedicated to the solution of Kalman-Yakubovic-Popov semi-definite programs (KYP-SDPs). These SDPs inherit their name from the KYP Lemma and they play a crucial role in e.g. robustness analysi
Externí odkaz:
http://arxiv.org/abs/2304.05037
Autor:
Gramlich, Dennis, Pauli, Patricia, Scherer, Carsten W., Allgöwer, Frank, Ebenbauer, Christian
This paper introduces a novel representation of convolutional Neural Networks (CNNs) in terms of 2-D dynamical systems. To this end, the usual description of convolutional layers with convolution kernels, i.e., the impulse responses of linear filters
Externí odkaz:
http://arxiv.org/abs/2303.03042
In this work, we propose a dissipativity-based method for Lipschitz constant estimation of 1D convolutional neural networks (CNNs). In particular, we analyze the dissipativity properties of convolutional, pooling, and fully connected layers making us
Externí odkaz:
http://arxiv.org/abs/2211.15253
Autor:
Gramlich, Dennis, Ebenbauer, Christian
In the present work, a simple algorithm for stabilizing an unknown linear time-invariant system is proposed, assuming only that this system is stabilizable. The suggested algorithm is based on first performing a partial identification of the system a
Externí odkaz:
http://arxiv.org/abs/2208.10392
Differential Dynamic Programming is an optimal control technique often used for trajectory generation. Many variations of this algorithm have been developed in the literature, including algorithms for stochastic dynamics or state and input constraint
Externí odkaz:
http://arxiv.org/abs/2205.12632
This paper is concerned with the training of neural networks (NNs) under semidefinite constraints, which allows for NN training with robustness and stability guarantees. In particular, we focus on Lipschitz bounds for NNs. Exploiting the banded struc
Externí odkaz:
http://arxiv.org/abs/2201.00632