Zobrazeno 1 - 10
of 474
pro vyhledávání: '"Seiler, Peter"'
The recently introduced structured input-output analysis is a powerful method for capturing nonlinear phenomena associated with incompressible flows, and this paper extends that method to the compressible regime. The proposed method relies upon a ref
Externí odkaz:
http://arxiv.org/abs/2407.14986
This paper derives a complete set of quadratic constraints (QCs) for the repeated ReLU. The complete set of QCs is described by a collection of $2^{n_v}$ matrix copositivity conditions where $n_v$ is the dimension of the repeated ReLU. We also show t
Externí odkaz:
http://arxiv.org/abs/2407.06888
Autor:
Lai, Joyce, Seiler, Peter
Online convex optimization (OCO) is a powerful tool for learning sequential data, making it ideal for high precision control applications where the disturbances are arbitrary and unknown in advance. However, the ability of OCO-based controllers to ac
Externí odkaz:
http://arxiv.org/abs/2405.07037
This paper presents sufficient conditions for the stability and $\ell_2$-gain performance of recurrent neural networks (RNNs) with ReLU activation functions. These conditions are derived by combining Lyapunov/dissipativity theory with Quadratic Const
Externí odkaz:
http://arxiv.org/abs/2405.05236
This letter considers assignment problems consisting of n pursuers attempting to intercept n targets. We consider stationary targets as well as targets maneuvering toward an asset. The assignment algorithm relies on an n x n cost matrix where entry (
Externí odkaz:
http://arxiv.org/abs/2404.08086
In this paper, a method is presented to synthesize neural network controllers such that the feedback system of plant and controller is dissipative, certifying performance requirements such as L2 gain bounds. The class of plants considered is that of
Externí odkaz:
http://arxiv.org/abs/2404.07373
Autor:
Kevian, Darioush, Syed, Usman, Guo, Xingang, Havens, Aaron, Dullerud, Geir, Seiler, Peter, Qin, Lianhui, Hu, Bin
In this paper, we explore the capabilities of state-of-the-art large language models (LLMs) such as GPT-4, Claude 3 Opus, and Gemini 1.0 Ultra in solving undergraduate-level control problems. Controls provides an interesting case study for LLM reason
Externí odkaz:
http://arxiv.org/abs/2404.03647
In this paper, we revisit model-free policy search on an important robust control benchmark, namely $\mu$-synthesis. In the general output-feedback setting, there do not exist convex formulations for this problem, and hence global optimality guarante
Externí odkaz:
http://arxiv.org/abs/2402.11654
Quadratic systems with lossless quadratic terms arise in many applications, including models of atmosphere and incompressible fluid flows. Such systems have a trapping region if all trajectories eventually converge to and stay within a bounded set. C
Externí odkaz:
http://arxiv.org/abs/2401.04787
Complex-valued Gaussian processes are commonly used in Bayesian frequency-domain system identification as prior models for regression. If each realization of such a process were an $H_\infty$ function with probability one, then the same model could b
Externí odkaz:
http://arxiv.org/abs/2312.10106