检索结果-内蒙古大学图书馆

chemtrain: Learning Deep Potential Models via Automatic Differentiation and Statistical Physics

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Fuchs, Paul Thaler, Stephan Röcken, Sebastien Zavadlav, Julija Multiscale Modeling of Fluid Materials Department of Engineering Physics and Computation TUM School of Engineering and Design Technical University of Munich Germany Valence Labs MontrealQC Canada Atomistic Modeling Center Munich Data Science Institute Technical University of Munich Germany

Neural Networks (NNs) are promising models for refining the accuracy of molecular dynamics, potentially opening up new fields of application. Typically trained bottom-up, atomistic NN potential models can reach firstprinciple accuracy, while coarse-grained implicit solvent NN potentials surpass classical continuum solvent models. However, overcoming the limitations of costly generation of accurate reference data and data inefficiency of common bottom-up training demands efficient incorporation of data from many sources. This paper introduces the framework chemtrain to learn sophisticated NN potential models through customizable training routines and advanced training algorithms. These routines can combine multiple top-down and bottom-up algorithms, e.g., to incorporate both experimental and simulation data or pre-train potentials with less costly algorithms. chemtrain provides an object-oriented high-level interface to simplify the creation of custom routines. On the lower level, chemtrain relies on JAX to compute gradients and scale the computations to use available resources. We demonstrate the simplicity and importance of combining multiple algorithms in the examples of parametrizing an all-atomistic model of titanium and a coarsegrained implicit solvent model of alanine dipeptide. Copyright © 2024, The Authors. All rights reserved.

关键词： Coarse-grained modeling

KLAP: KYP LEMMA BASED LOW-RANK APPROXIMATION FOR H2-OPTIMAL PASSIVATION

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Nicodemus, Jonas Voigt, Matthias Gugercin, Serkan Unger, Benjamin University of Stuttgart Universitätsstr. 32 Stuttgart70569 Germany Department of Mathematics Division of Computational Modeling and Data Analytics Academy of Data Science Virginia Tech BlacksburgVA24061 United States Faculty of Mathematics and Computer Science UniDistance Suisse Schinerstr. 18 Brig3900 Switzerland

We present a novel passivity enforcement (passivation) method, called KLAP, for linear time-invariant systems based on the Kalman-Yakubovich-Popov (KYP) lemma and the closely related Lur’e equations. The passivation problem in our framework corresponds to finding a perturbation to a given non-passive system that renders the system passive while minimizing the H2 or frequency-weighted H2 distance between the original non-passive and the resulting passive system. We show that this problem can be formulated as an unconstrained optimization problem whose objective function can be differentiated efficiently even in large-scale settings. We show that any minimizer of the unconstrained problem yields the same passive system. Furthermore, we prove that, in the absence of a feedthrough term, every local minimizer is also a global minimizer. For cases involving a non-trivial feedthrough term, we analyze global minimizers in relation to the extremal solutions of the Lur’e equations, which can serve as tools for identifying local minima. To solve the resulting numerical optimization problem efficiently, we propose an initialization strategy based on modifying the feedthrough term and a restart strategy when it is likely that the optimization has converged to a local minimum. Numerical examples illustrate the effectiveness of the proposed *** Codes 37J06, 37M99, 65P10, 93A30, 93B30, 93C05 © 2025, CC BY.

关键词： Convergence of numerical methods

An Efficient Model based on Machine Learning Algorithms for Virtual Machines Classification in Cloud Computing Environment 4

学校读者我要写书评

暂无评论

An Efficient Model based on Machine Learning Algorithms for ...

4th International Conference on Innovative Research in Applied science, Engineering and Technology, IRASET 2024

作者： Amahrouch, Abdelhadi Bouhamidi, Mehdi Saadi, Youssef El Kafhali, Said Sultan Moulay Slimane University Faculty Of Sciences And Techniques Data Science For Sustainable Earth Laboratory B.P. 523 Beni Mellal23000 Morocco Polytechnic University Laboratory Of Industrial And Human Automation Mechanics And Computer Science Hauts-de-France France Hassan First University Of Settat Faculty Of Sciences And Techniques Computer Networks Modeling And Mobility Laboratory B.P. 539 Settat26000 Morocco

ISBN: (纸本)9798350309508

In cloud computing, virtual machines consolidation (VMC) techniques are commonly used to improve resource utilization and reduce energy consumption. Task scheduling in cloud systems is a crucial aspect of VMC as it involves mapping clients' requirements to the appropriate computing resources such as Virtual Machines (VMs) or Physical Machines (PMs). The cloud provider must ensure that tasks are executed efficiently using the available shared computing resources while maintaining the quality of service (QoS) and minimizing the carbon footprint. Therefore, a good VM migration based on the customer's needs and IT resource capacity is required to maintain the best performance of the cloud system. In this work, we introduce an approach that leverage machine learning-based algorithms for VMs classification based on their latency sensitivity to facilitate subsequent migration into a suitable PM for better VMC. These algorithms categorize VMs into two groups: potentially inter-active machines (exhibiting periodic behavior on a daily scale) and latency-insensitive machines (for example, batch workloads, development, and test workloads). Our model demonstrated robust performance, achieving an accuracy of around 83%, thus establishing itself as the most proficient classifier in this study. © 2024 IEEE.

关键词： Virtual machine

Using LDLT factorizations in Newton's method for solving general large-scale algebraic Riccati equations

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Saak, Jens Werner, Steffen W.R. Max Planck Institute for Dynamics of Complex Technical Systems Sandtorstraße 1 Magdeburg39106 Germany Department of Mathematics Division of Computational Modeling and Data Analytics Academy of Data Science Virginia Tech BlacksburgVA24061 United States

Continuous-time algebraic Riccati equations can be found in many disciplines in different forms. In the case of small-scale dense coefficient matrices, stabilizing solutions can be computed to all possible formulations of the Riccati equation. This is not the case when it comes to large-scale sparse coefficient matrices. In this paper, we provide a reformulation of the Newton-Kleinman iteration scheme for continuous-time algebraic Riccati equations using indefinite symmetric low-rank factorizations. This allows the application of the method to the case of general large-scale sparse coefficient matrices. We provide convergence results for several prominent realizations of the equation and show in numerical examples the effectiveness of the *** Codes 15A24, 49M15, 65F45, 65H10, 93A15 Copyright © 2024, The Authors. All rights reserved.

关键词： Continuous time systems

A plastic damage model with mixed isotropic-kinematic hardening for low-cycle fatigue in 7020 aluminum

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Daneshyar, Alireza Siebert, Dorina Radlbeck, Christina Kollmannsberger, Stefan Chair of Computational Modeling and Simulation Technical University of Munich Germany Chair of Metal Structures Technical University of Munich Germany Data Science in Civil Engineering Bauhaus-Universität Weimar Germany

The paper at hand presents an in-depth investigation into the fatigue behavior of the high-strength aluminum alloy EN AW-7020 T6 using both experimental and numerical approaches. Two types of specimens are investigated: a dog-bone specimen subjected to cyclic loading in a symmetric strain-controlled regime, and a compact tension specimen subjected to repeated loading and unloading, which leads to damage growth from the notch tip. Experimental data from these tests are used to identify the different phases of fatigue and to establish the requirements for an appropriate constitutive model. Subsequently, a plastic-damage model is developed, incorporating J2 plasticity with Chaboche-type mixed isotropic-kinematic hardening. A detailed investigation reveals that the Chaboche model must be blended with a suitable isotropic hardening and combined with a proper damage growth model to accurately describe cyclic fatigue including large plastic strains up to failure. Multiple back-stress components with independent properties are superimposed, and exponential isotropic hardening with saturation effects is introduced to improve alignment with experimental results. For damage, different stress splits are tested, with the deviatoric/volumetric split proving successful in reproducing the desired degradation in peak stress and stiffness. A nonlinear activation function is introduced to ensure smooth transitions between tension and compression. Two damage indices, one for the deviatoric part and one for the volumetric part, are defined, each of which is governed by a distinct trilinear damage growth function. The governing differential equation of the problem is regularized by higher-order gradient terms to address the ill-posedness induced by softening. Finally, the plasticity model is calibrated using finite element simulations of the dog-bone test and subsequently applied to the cyclic loading of the compact tension specimen. © 2025, CC BY-NC-ND.

关键词： Cyclic loads

A Synchronous Parallel Method with Parameters Communication Prediction for Distributed Machine Learning 19th

学校读者我要写书评

暂无评论

A Synchronous Parallel Method with Parameters Communication...

19th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing, CollaborateCom 2023

作者： Zeng, Yanguo Xue, Meiting Xu, Peiran Shi, Yukun Zeng, Kaisheng Zhang, Jilin Yue, Lupeng School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China Key Laboratory for Modeling and Simulation of Complex Systems Ministry of Education Hangzhou310018 China Data Security Governance Zhejiang Engineering Research Center Hangzhou310018 China National University of Defense Technology Changsha China School of Cyberspace HangZhou Dianzi University Hangzhou China Department of Computer Science and Technology Tsinghua University Beijing China

ISBN: (纸本)9783031545306

With the development of machine learning technology in various fields, such as medical care, smart manufacturing, etc., the data has exploded. It is a challenge to train a deep learning model for different application domains with large-scale data and limited resources of a single device. The distributed machine-learning technology, which uses a parameter server and multiple clients to train a model collaboratively, is an excellent method to solve this problem. However, it needs much communication between different devices with limited communication resources. The stale synchronous parallel method is a mainstream communication method to solve this problem, but it always leads to high synchronization delay and low computing efficiency as the inappropriate delay threshold value set by the user based on experience. This paper proposes a synchronous parallel method with parameters communication prediction for distributed machine learning. It predicts the optimal timing for synchronization, which can solve the problem of long synchronization waiting time caused by the inappropriate threshold settings in the stale synchronous parallel method. Moreover, it allows fast nodes to continue local training while performing global synchronization, which can improve the resource utilization of work nodes. Experimental results show that compared with the delayed synchronous parallel method, the training time and quality, and resource usage of our method are both significantly improved. © ICST Institute for Computer sciences, Social Informatics and Telecommunications Engineering 2024.

关键词： Forecasting

Variational Interface Physics Informed Neural Networks (VI-PINNs) for Heterogeneous Subsurface Systems 57

学校读者我要写书评

暂无评论

Variational Interface Physics Informed Neural Networks (VI-P...

57th US Rock Mechanics/Geomechanics Symposium

作者： Sarma, A.K. Annavarapu, C. Roy, P. Jagannathan, S. Valiveti, D.M. Department of Civil Engineering IIT Madras Tamil Nadu Chennai India Atmospheric Earth and Energy Division Lawrence Livermore National Laboratory LivermoreCA United States Santa Clara CA United States Modeling Optimization and Data Science ExxonMobil Technology and Engineering SpringTX United States

ISBN: (纸本)9780979497582

This study presents a novel approach to Physics Informed Neural Networks (PINNs) called Variational Interface PINNs (VI-PINNs) for modeling physical systems with material interfaces. In conventional PINNs, a loss functional obtained from the residual of the strong form of governing equations is minimized to estimate the variable of interest. By contrast, the presented approach relies on minimizing the potential energy functional of a physical system using artificial neural networks. Firstly, we present appropriate modifications to the neural network architecture so that material interfaces can be captured effectively in a variational framework using neural networks. Secondly, we incorporate the interface coupling conditions in the energy functionals to be minimized using VI-PINNs. Thirdly, we examine several numerical integration techniques and compare their accuracy and cost to evaluate the Lagrangians in the VI-PINNs framework. Finally, we discuss a variationally consistent penalty approach to enforce boundary and interface conditions better. Several benchmark 1D and 2D examples are solved using the proposed method and conventional PINNs. Their performances are then compared in terms of cost and accuracy, and their relative strengths and weaknesses are identified. © 2023 57th US Rock Mechanics/Geomechanics Symposium. All Rights Reserved.

关键词： Neural networks

Predicting solvation free energies with an implicit solvent machine learning potential

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Röcken, Sebastien Burnet, Anton F. Zavadlav, Julija Department of Engineering Physics and Computation TUM School of Engineering and Design Technical University of Munich Germany Atomistic Modeling Center Munich Data Science Institute Technical University of Munich Germany

Machine learning (ML) potentials are a powerful tool in molecular modeling, enabling ab initio accuracy for comparably small computational costs. Nevertheless, all-atom simulations employing best-performing graph neural network architectures are still too expensive for applications requiring extensive sampling, such as free energy computations. Implicit solvent models could provide the necessary speed-up due to reduced degrees of freedom and faster dynamics. Here, we introduce a Solvation Free Energy Path Reweighting (ReSolv) framework to parametrize an implicit solvent ML potential for small organic molecules that accurately predicts the hydration free energy, an essential parameter in drug design and pollutant modeling. With a combination of top-down (experimental hydration free energy data) and bottom-up (ab initio data of molecules in a vacuum) learning, ReSolv bypasses the need for intractable ab initio data of molecules in explicit bulk solvent and does not have to resort to less accurate data-generating models. On the FreeSolv dataset, ReSolv achieves a mean absolute error close to average experimental uncertainty, significantly outperforming standard explicit solvent force fields. Compared to the explicit solvent ML potential, ReSolv offers a computational speedup of four orders of magnitude and attains closer agreement with experiments. The presented framework paves the way toward deep molecular models that are more accurate yet computationally cheaper than classical atomistic models. Copyright © 2024, The Authors. All rights reserved.

关键词： Solvation

Reversible data Hiding in Encrypted Images Based on Multi-Predictor and Quad-tree Block Encoding 2022

学校读者我要写书评

暂无评论

Reversible Data Hiding in Encrypted Images Based on Multi-Pr...

7th International Conference on Intelligent Information Technology, ICIIT 2022

作者： Zhang, Huiqi Li, Lin Li, Qingyan School Of Science Jimei University Xiamen361021 China Computer Engineering College Jimei University Xiamen361021 China Digital Fujian Big Data Modeling And Intelligent Computing Institute Jimei University Xiamen361021 China

ISBN: (纸本)9781450396172

With the rapid development of the Internet, people's awareness of privacy protection is also gradually improved. Reversible data hiding of encrypted image is a technique that encrypts the original image and allows the embedding of secret data without knowing the original image information. This method can accurately extract the secret data and reconstruct the original image completely. In this paper, a reversible data hiding algorithm of encrypted image based on multi-predictor and quad-tree block encoding is proposed. First, the original image is divided into 8×8 non-overlapping blocks. Then, multi-predictor is used to predict each block to get the prediction error image, then block scrambling is used to encrypt it. Since the pixel values of the encrypted image are small integer closes to zero, the quad-tree block encoding method can be used to embed a large amount of data. Experimental results show that the embedding rate of this method is better than that of some new algorithms. © 2022 ACM.

关键词： Embeddings