Zobrazeno 1 - 10
of 89
pro vyhledávání: '"Mohr, Ryan"'
Autor:
Mezic, Igor, Drmac, Zlatko, Crnjaric-Zic, Nelida, Macesic, Senka, Fonoberova, Maria, Mohr, Ryan, Avila, Allan, Manojlovic, Iva, Andrejcuk, Aleksandr
The problem of prediction of behavior of dynamical systems has undergone a paradigm shift in the second half of the 20th century with the discovery of the possibility of chaotic dynamics in simple, physical, dynamical systems for which the laws of ev
Externí odkaz:
http://arxiv.org/abs/2304.13601
Autor:
Redman, William T., Bello-Rivas, Juan M., Fonoberova, Maria, Mohr, Ryan, Kevrekidis, Ioannis G., Mezić, Igor
Study of the nonlinear evolution deep neural network (DNN) parameters undergo during training has uncovered regimes of distinct dynamical behavior. While a detailed understanding of these phenomena has the potential to advance improvements in trainin
Externí odkaz:
http://arxiv.org/abs/2302.09160
This paper introduces a reduced order modeling technique based on Koopman operator theory that gives confidence bounds on the model's predictions. It is based on a data-driven spectral decomposition of said operator. The reduced order model is constr
Externí odkaz:
http://arxiv.org/abs/2209.13127
Iterative algorithms are of utmost importance in decision and control. With an ever growing number of algorithms being developed, distributed, and proprietarized, there is a similarly growing need for methods that can provide classification and compa
Externí odkaz:
http://arxiv.org/abs/2209.06374
The discovery of sparse subnetworks that are able to perform as well as full models has found broad applied and theoretical interest. While many pruning methods have been developed to this end, the na\"ive approach of removing parameters based on the
Externí odkaz:
http://arxiv.org/abs/2110.14856
Hierarchical support vector regression (HSVR) models a function from data as a linear combination of SVR models at a range of scales, starting at a coarse scale and moving to finer scales as the hierarchy continues. In the original formulation of HSV
Externí odkaz:
http://arxiv.org/abs/2012.11734
Autor:
Manojlović, Iva, Fonoberova, Maria, Mohr, Ryan, Andrejčuk, Aleksandr, Drmač, Zlatko, Kevrekidis, Yannis, Mezić, Igor
We consider the training process of a neural network as a dynamical system acting on the high-dimensional weight space. Each epoch is an application of the map induced by the optimization algorithm and the loss function. Using this induced map, we ca
Externí odkaz:
http://arxiv.org/abs/2006.11765
This paper presents a novel learning framework to construct Koopman eigenfunctions for unknown, nonlinear dynamics using data gathered from experiments. The learning framework can extract spectral information from the full nonlinear dynamics by learn
Externí odkaz:
http://arxiv.org/abs/1911.08751
This paper proposes a new computational method for solving structured least squares problems that arise in the process of identification of coherent structures in fluid flows. It is deployed in combination with dynamic mode decomposition (DMD) which
Externí odkaz:
http://arxiv.org/abs/1811.12562
The goals and contributions of this paper are twofold. It provides a new computational tool for data driven Koopman spectral analysis by taking up the formidable challenge to develop a numerically robust algorithm by following the natural formulation
Externí odkaz:
http://arxiv.org/abs/1808.09557