English
Related papers

Related papers: Robustness Analysis of Continuous-Depth Models wit…

200 papers

Deep residual networks (ResNets) have demonstrated outstanding success in computer vision tasks, attributed to their ability to maintain gradient flow through deep architectures. Simultaneously, controlling the Lipschitz constant in neural…

Machine Learning · Computer Science 2025-12-08 Marius F. R. Juston , Ramavarapu S. Sreenivas , Dustin Nottage , Ahmet Soylemezoglu

We present a systematic account of recent developments of the relativistic Lattice Boltzmann method (RLBM) for dissipative hydrodynamics. We describe in full detail a unified, compact and dimension-independent procedure to design…

High Energy Physics - Lattice · Physics 2020-05-29 A. Gabbana , D. Simeoni , S. Succi , R. Tripiccione

We propose an enhanced wall-boundary treatment for the lattice Boltzmann method (LBM), designed for high-Reynolds-number turbulent flows on adaptively refined Cartesian grids. The method improves the slip-velocity bounce-back scheme by…

Fluid Dynamics · Physics 2026-01-27 Jorge Ponsin , Carlos Lozano

We consider learning the structures of Gaussian latent tree models with vector observations when a subset of them are arbitrarily corrupted. First, we present the sample complexities of Recursive Grouping (RG) and Chow-Liu Recursive…

Machine Learning · Statistics 2021-10-26 Fengzhuo Zhang , Vincent Y. F. Tan

Explainability models are now prevalent within machine learning to address the black-box nature of neural networks. The question now is which explainability model is most effective. Probabilistic Lipschitzness has demonstrated that the…

Machine Learning · Computer Science 2024-03-11 Lachlan Simpson , Kyle Millar , Adriel Cheng , Cheng-Chew Lim , Hong Gunn Chew

This paper presents a one-shot learning approach with performance and robustness guarantees for the linear quadratic regulator (LQR) control of stochastic linear systems. Even though data-based LQR control has been widely considered,…

Systems and Control · Electrical Eng. & Systems 2024-10-29 Ramin Esmzad , Hamidreza Modares

Lagrangian Neural Networks (LNNs) can learn arbitrary Lagrangians from trajectory data, but their unusual optimization objective leads to significant training instabilities that limit their application to complex systems. We propose several…

Machine Learning · Computer Science 2026-01-21 Abdullah Umut Hamzaogullari , Arkadas Ozakin

Certified robustness is a critical property for deploying neural networks (NN) in safety-critical applications. A principle approach to achieving such guarantees is to constrain the global Lipschitz constant of the network. However,…

Machine Learning · Computer Science 2025-07-01 Zain ul Abdeen , Vassilis Kekatos , Ming Jin

Lagrangian Particle Tracking (LPT) enables practitioners to study various concepts in turbulence by measuring particle positions in flows of interest. This data is subject to measurement errors, and filtering techniques are applied to…

Fluid Dynamics · Physics 2026-01-16 Griffin M. Kearney , Kasey M. Laurent , Reece V. Kearney

We study statistical inference and distributionally robust solution methods for stochastic optimization problems, focusing on confidence intervals for optimal values and solutions that achieve exact coverage asymptotically. We develop a…

Machine Learning · Statistics 2018-07-03 John Duchi , Peter Glynn , Hongseok Namkoong

Sliced Wasserstein distances preserve properties of classic Wasserstein distances while being more scalable for computation and estimation in high dimensions. The goal of this work is to quantify this scalability from three key aspects: (i)…

Machine Learning · Statistics 2022-10-18 Sloan Nietert , Ritwik Sadhu , Ziv Goldfeld , Kengo Kato

Learning-based approaches for controlling safety-critical systems are rapidly growing in popularity; thus, it is important to assure their performance and safety. Hamilton-Jacobi (HJ) reachability analysis is a popular formal verification…

Robotics · Computer Science 2024-04-11 Albert Lin , Somil Bansal

Robustness of deep neural networks against adversarial perturbations is a pressing concern motivated by recent findings showing the pervasive nature of such vulnerabilities. One method of characterizing the robustness of a neural network…

Machine Learning · Statistics 2021-03-15 Hisham Husain , Borja Balle

The immersed boundary method is a mathematical framework for modeling fluid-structure interaction. This formulation describes the momentum, viscosity, and incompressibility of the fluid-structure system in Eulerian form, and it uses…

Numerical Analysis · Mathematics 2020-02-26 Ben Vadala-Roth , Shashank Acharya , Neelesh A Patankar , Simone Rossi , Boyce E Griffith

We consider the problem of analyzing and designing gradient-based discrete-time optimization algorithms for a class of unconstrained optimization problems having strongly convex objective functions with Lipschitz continuous gradient. By…

Optimization and Control · Mathematics 2025-10-20 Simon Michalowsky , Carsten Scherer , Christian Ebenbauer

The Robust Satisficing (RS) model is an emerging approach to robust optimization, offering streamlined procedures and robust generalization across various applications. However, the statistical theory of RS remains unexplored in the…

Machine Learning · Statistics 2024-06-03 Zhiyi Li , Yunbei Xu , Ruohan Zhan

The robustness of neural networks against input perturbations with bounded magnitude represents a serious concern in the deployment of deep learning models in safety-critical systems. Recently, the scientific community has focused on…

Machine Learning · Computer Science 2023-11-29 Bernd Prach , Fabio Brau , Giorgio Buttazzo , Christoph H. Lampert

We present a framework based on the generalized lattice-Boltzmann equation using multiple relaxation times with forcing term for eddy capturing simulation of wall bounded turbulent flows. Due to its flexibility in using disparate relaxation…

Computational Physics · Physics 2009-11-13 Kannan N. Premnath , Martin J. Pattison , Sanjoy Banerjee

High sensitivity of neural networks against malicious perturbations on inputs causes security concerns. To take a steady step towards robust classifiers, we aim to create neural network models provably defended from perturbations. Prior…

Computer Vision and Pattern Recognition · Computer Science 2018-11-02 Yusuke Tsuzuku , Issei Sato , Masashi Sugiyama

Deep learning has achieved remarkable success across a wide range of tasks, but its models often suffer from instability and vulnerability: small changes to the input may drastically affect predictions, while optimization can be hindered by…

Machine Learning · Computer Science 2025-10-30 Blaise Delattre