English
Related papers

Related papers: The Neutrality Boundary Framework: Quantifying Sta…

200 papers

Graph neural networks (GNNs) have been proved powerful in graph-oriented tasks. However, many real-world graphs are heterophilous, challenging the homophily assumption of classical GNNs. To solve the universality problem, many studies…

Machine Learning · Computer Science 2023-10-09 Shengbo Gong , Jiajun Zhou , Chenxuan Xie , Qi Xuan

A generalized dynamical robust nonlinear filtering framework is established for a class of Lipschitz differential algebraic systems, in which the nonlinearities appear both in the state and measured output equations. The system is assumed…

Systems and Control · Computer Science 2014-02-25 Masoud Abbaszadeh

Antifragility is a property that enhances the capability of a system in response to external perturbations. Although the concept has been applied in many areas, a practical measure of antifragility has not been developed yet. Here we…

Adaptation and Self-Organizing Systems · Physics 2026-02-04 Omar K. Pineda , Hyobin Kim , Carlos Gershenson

One of the main necessities for population geneticists is the availability of statistical tools that enable to accept or reject the neutral Wright-Fisher model with high power. A number of statistical tests have been developed to detect…

Quantitative Methods · Quantitative Biology 2010-11-08 Luca Ferretti , Giacomo Marmorini , Sebastian Ramos-Onsins

In recent years, plenty of metrics have been proposed to identify networks that are free of gradient explosion and vanishing. However, due to the diversity of network components and complex serial-parallel hybrid connections in modern DNNs,…

Machine Learning · Computer Science 2020-08-13 Zhaodong Chen , Lei Deng , Bangyan Wang , Guoqi Li , Yuan Xie

This paper presents a general framework for estimating high-dimensional conditional latent factor models via constrained nuclear norm regularization. We establish large sample properties of the estimators and provide efficient algorithms…

Econometrics · Economics 2025-12-09 Qihui Chen

In this paper, we address the problem of synthesizing safe and stabilizing controllers for nonlinear systems subject to complex safety specifications and input constraints. We introduce the Universal Barrier Function (UBF), a single…

Systems and Control · Electrical Eng. & Systems 2025-11-04 Vrushabh Zinage , Efstathios Bakolas

We introduce a manifold analysis technique for neural network representations. Normalized Space Alignment (NSA) compares pairwise distances between two point clouds derived from the same source and having the same size, while potentially…

Machine Learning · Computer Science 2024-11-08 Danish Ebadulla , Aditya Gulati , Ambuj Singh

We propose improvements in numerical evaluation of symmetric stable density and its partial derivatives with respect to the parameters. They are useful for more reliable evaluation of maximum likelihood estimator and its standard error.…

Statistics Theory · Mathematics 2007-06-13 Muneya Matsui , Akimichi Takemura

Machine learning (ML) techniques, especially neural networks (NNs), have shown promise in learning subgrid-scale parameterizations for climate models. However, a major problem with data-driven parameterizations, particularly those learned…

Atmospheric and Oceanic Physics · Physics 2024-07-17 Hamid A. Pahlavan , Pedram Hassanzadeh , M. Joan Alexander

The problem of adversarial examples has shown that modern Neural Network (NN) models could be rather fragile. Among the more established techniques to solve the problem, one is to require the model to be {\it $\epsilon$-adversarially…

Machine Learning · Computer Science 2020-11-17 Yuxin Wen , Shuai Li , Kui Jia

We study the robustness of system estimation to parametric perturbations in system dynamics and initial conditions. We define the problem of sensitivity-based parametric uncertainty quantification in dynamical system estimation. The main…

Systems and Control · Electrical Eng. & Systems 2025-09-09 Ayush Pandey

Engineering simulations using boundary-value partial differential equations often implicitly assume that the uncertainty in the location of the boundary has a negligible impact on the output of the simulation. In this work, we develop a…

Tissues and Organs · Quantitative Biology 2024-06-11 S. Gerry Gralton , Farah Alkhatib , Ben Zwick , George Bourantas , Adam Wittek , Karol Miller

We present an information-based uncertainty quantification method for general Markov Random Fields. Markov Random Fields (MRF) are structured, probabilistic graphical models over undirected graphs, and provide a fundamental unifying…

Machine Learning · Statistics 2021-07-20 Panagiota Birmpa , Markos A. Katsoulakis

The Lipschitz bound, a technique from robust statistics, can limit the maximum changes in the output concerning the input, taking into account associated irrelevant biased factors. It is an efficient and provable method for examining the…

Machine Learning · Computer Science 2023-12-13 Yaning Jia , Chunhui Zhang

We investigate the renormalisation of Einstein gravity using a novel subtraction scheme in dimensional regularisation. The one-loop beta function for Newton's constant receives contributions from poles in even dimensions and can be mapped…

High Energy Physics - Theory · Physics 2025-09-15 Kevin Falls , Renata Ferrero

Neural networks (NNs) are now routinely implemented on systems that must operate in uncertain environments, but the tools for formally analyzing how this uncertainty propagates to NN outputs are not yet commonplace. Computing tight bounds…

Machine Learning · Computer Science 2020-12-08 Michael Everett , Golnaz Habibi , Jonathan P. How

In this note we derive an upper bound for the Hausdorff dimension of the stable set of a hyperbolic set $\Lambda$ of a $C^2$ diffeomorphisms on a $n$-dimensional manifold. As a consequence we obtain that $\dim_H W^s(\Lambda)=n$ is…

Dynamical Systems · Mathematics 2007-05-23 Rasul Shafikov , Christian Wolf

Despite the robustness of complex networks has been extensively studied in the last decade, there still lacks a unifying framework able to embrace all the proposed metrics. In the literature there are two open issues related to this gap:…

Social and Information Networks · Computer Science 2014-07-01 Marc Manzano , Faryad Sahneh , Caterina Scoglio , Eusebi Calle , Jose Luis Marzo

We propose a systematic analysis of deep neural networks (DNNs) based on a signal processing technique for network parameter removal, in the form of synaptic filters that identifies the fragility, robustness and antifragility…

Machine Learning · Computer Science 2023-12-27 Chandresh Pravin , Ivan Martino , Giuseppe Nicosia , Varun Ojha