Robust, positive and exact model reduction via monotone matrices
This work focuses on the problem of exact model reduction of positive linear systems, by leveraging minimal realization theory. While determining the existence of a positive reachable realization remains in general an open problem, we are able to fully characterize the cases in which the new model is obtained with non-negative reduction matrices, and hence positivity of the reduced model is robust with respect to small perturbations of the original system. The characterization is obtained by specializing monotone matrix theory to positive matrices. In addition, we provide a systematic method to construct positive reductions also when minimal ones are not available, by exploiting algebraic techniques.
Code (0)
등록된 구현이 없습니다.
Tasks
modelSimilar Papers 제목 키워드 기반
ITSPACE: Monotone Gaussian Optimal Transport Updates
Covariance matrices serve as compact descriptors of feature distributions in many machine-learning pipelines, including domain adaptation and Gaussian embeddings. Under a centered Gaussian approximation, the unregularize…
Domain AdaptationMuon Dynamics as a Spectral Wasserstein Flow
Gradient normalization stabilizes deep-learning optimization, and spectral normalizations are especially natural for matrix-shaped parameter blocks; Muon is the motivating example. We study an idealized deterministic, co…
Explaining Deep Network Classification of Matrices: A Case Study on Monotonicity
This work demonstrates a methodology for using deep learning to discover simple, practical criteria for classifying matrices based on abstract algebraic properties. By combining a high-performance neural network with exp…
EPEM: Efficient Parameter Estimation for Multiple Class Monotone Missing Data
The problem of monotone missing data has been broadly studied during the last two decades and has many applications in different fields such as bioinformatics or statistics. Commonly used imputation techniques require mu…
Imputationparameter estimationPositive Neural Networks in Discrete Time Implement Monotone-Regular Behaviors
We study the expressive power of positive neural networks. The model uses positive connection weights and multiple input neurons. Different behaviors can be expressed by varying the connection weights. We show that in di…