检索结果-内蒙古大学图书馆

Foundation Models for Atomistic Simulation of Chemistry and Materials

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Yuan, Eric C.-Y. Liu, Yunsheng Chen, Junmin Zhong, Peichen Raja, Sanjeev Kreiman, Tobias Vargas, Santiago Xu, Wenbin Head-Gordon, Martin Yang, Chao Blau, Samuel M. Cheng, Bingqing Krishnapriyan, Aditi Head-Gordon, Teresa Kenneth S. Pitzer Theory Center Department of Chemistry United States Department of Chemical and Biomolecular Engineering United States Electrical Engineering and Computer Science United States Bakar Institute of Digital Materials for the Planet University of California BerkeleyCA94720 United States Chemical Sciences Division United States Applied Mathematics and Computational Research Division United States Energy Technologies Area United States National Energy Research Scientific Computing Center Lawrence Berkeley National Laboratory BerkeleyCA94720 United States

Given the power of large language and large vision models, it is of profound and fundamental interest to ask if a foundational model based on data and parameter scaling laws and pre-training strategies is possible for learned simulations of chemistry and materials. The scaling of large and diverse datasets and highly expressive architectures for chemical and materials sciences should result in a foundation model that is more efficient and broadly transferable, robust to out-of-distribution challenges, and easily fine-tuned to a variety of downstream observables, when compared to specific training from scratch on targeted applications in atomistic simulation. In this Perspective we aim to cover the rapidly advancing field of machine learned interatomic potentials (MLIP), and to illustrate a path to create chemistry and materials MLIP foundation models at larger scale. © 2025, CC BY-SA.

关键词：

TensorKMC: Kinetic Monte Carlo Simulation of 50 Trillion Atoms Driven by Deep Learning on a New Generation of Sunway Supercomputer

学校读者我要写书评

暂无评论

TensorKMC: Kinetic Monte Carlo Simulation of 50 Trillion Ato...

Supercomputing Conference

作者： Honghui Shang Xin Chen Xingyu Gao Rongfen Lin Lifang Wang Fang Li Qian Xiao Lei Xu Qiang Sun Leilei Zhu Fei Wang Yunquan Zhang Haifeng Song SKL of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing China Institute of Applied Physics and Computational Mathematics Beijing China Department of Computer Science and Technology Tsinghua University Wuxin China National Supercomputer Center in Wuxi Wuxi China

ISBN: (数字)9781450384421

ISBN: (纸本)9781665483902

The atomic kinetic Monte Carlo method plays an important role in multi-scale physical simulations because it bridges the micro and macro worlds. However, its accuracy is limited by empirical potentials. We therefore propose herein a triple-encoding algorithm and vacancy-cache mechanism to efficiently integrate ab initio neural network potentials (NNPs) with AKMC and implement them in our TensorKMC codes. We port our program to SW26010-pro and innovate a fast feature operator and a big fusion operator for the NNPs for fully utilizing the powerful heterogeneous computing units of the new-generation Sunway supercomputer. We further optimize memory usage. With these improvements, TensorKMC can simulate up to 54 trillions of atoms and achieve excellent strong and weak scaling performance up to 27,456,000 cores.

关键词： Technological innovation Monte Carlo methods Codes Quantum chemistry High performance computing Optimization methods Artificial neural networks

Position: Bayesian deep learning is needed in the age of large-scale AI 24

学校读者我要写书评

暂无评论

Position: Bayesian deep learning is needed in the age of lar...

Proceedings of the 41st International Conference on Machine Learning

作者： Theodore Papamarkou Maria Skoularidou Konstantina Palla Laurence Aitchison Julyan Arbel David Dunson Maurizio Filippone Vincent Fortuin Philipp Hennig José Miguel Hernández-Lobato Aliaksandr Hubin Alexander Immer Theofanis Karaletsos Mohammad Emtiyaz Khan Agustinus Kristiadi Yingzhen Li Stephan Mandt Christopher Nemeth Michael A. Osborne Tim G. J. Rudner David Rügamer Yee Whye Teh Max Welling Andrew Gordon Wilson Ruqi Zhang Department of Mathematics The University of Manchester Manchester UK Eric and Wendy Schmidt Center Broad Institute of MIT and Harvard Cambridge Spotify London UK Computational Neuroscience Unit University of Bristol Bristol UK Centre Inria de l'Université Grenoble Alpes Grenoble France Department of Statistical Science Duke University Statistics Program KAUST Saudi Arabia Helmholtz AI Munich Germany and Department of Computer Science Technical University of Munich Munich Germany and Munich Center for Machine Learning Munich Germany Tübingen AI Center University of Tübingen Tübingen Germany Department of Engineering University of Cambridge Cambridge UK Department of Mathematics University of Oslo Oslo Norway and Bioinformatics and Applied Statistics Norwegian University of Life Sciences Ås Norway Department of Computer Science ETH Zurich Switzerland Chan Zuckerberg Initiative California Center for Advanced Intelligence Project RIKEN Tokyo Japan Vector Institute Toronto Canada Department of Computing Imperial College London London UK Department of Computer Science UC Irvine Irvine Department of Mathematics and Statistics Lancaster University Lancaster UK Department of Engineering Science University of Oxford Oxford UK Center for Data Science New York University New York Munich Center for Machine Learning Munich Germany and Department of Statistics LMU Munich Munich Germany DeepMind London UK and Department of Statistics University of Oxford Oxford UK Informatics Institute University of Amsterdam Amsterdam Netherlands Courant Institute of Mathematical Sciences and Center for Data Science Computer Science Department New York University New York Department of Computer Science Purdue University West Lafayette

In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language datasets. However, a broader perspective reveals a multitude of overlooked metrics, tasks, and data types, such as uncertainty, active and continual learning, and scientific data, that demand attention. Bayesian deep learning (BDL) constitutes a promising avenue, offering advantages across these diverse settings. This paper posits that BDL can elevate the capabilities of deep learning. It revisits the strengths of BDL, acknowledges existing challenges, and highlights some exciting research avenues aimed at addressing these obstacles. Looking ahead, the discussion focuses on possible ways to combine large-scale foundation models with BDL to unlock their full potential.

关键词：

Semantic preserving bijective mappings of mathematical formulae between document preparation systems and computer algebra systems

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Cohl, Howard S. Schubotz, Moritz Youssef, Abdou Greiner-Petter, André Gerhard, Jürgen Saunders, Bonita V. McClain, Marjorie A. Applied and Computational Mathematics Division NIST GaithersburgMD United States Dept. of Computer and Information Science University of Konstanz Konstanz Germany Dept. of Computer Science GWU WashingtonDC United States DSIMG Technische Universität Berlin Germany Maplesoft WaterlooON Canada

Document preparation systems like LaTeX offer the ability to render mathematical expressions as one would write these on paper. Using LaTeX, LaTeXML, and tools generated for use in the National Institute of Standards (NIST) Digital Library of Mathematical Functions, semantically enhanced mathematical LaTeX markup (semantic LaTeX) is achieved by using a semantic macro set. computer algebra systems (CAS) such as Maple and Mathematica use alternative markup to represent mathematical expressions. By taking advantage of Youssef's Part-of-Math tagger and CAS internal representations, we develop algorithms to translate mathematical expressions represented in semantic LaTeX to corresponding CAS representations and vice versa. We have also developed tools for translating the entire Wolfram Encoding Continued Fraction Knowledge and University of Antwerp Continued Fractions for Special Functions datasets, for use in the NIST Digital Repository of Mathematical Formulae. The overall goal of these efforts is to provide semantically enriched standard conforming MathML representations to the public for formulae in digital mathematics libraries. These representations include presentation MathML, content MathML, generic LaTeX, semantic LaTeX, and now CAS representations as well. © 2021, CC BY.

关键词： Semantics

Improving the Accuracy of the Variational Quantum Eigensolver for Molecular Systems by the Explicitly-Correlated Perturbative R12-Correction

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Schleich, Philipp Kottmann, Jakob S. Aspuru-Guzik, Alan Department of Computer Science University of Toronto Canada Applied and Computational Mathematics Department of Mathematics Rwth Aachen University Aachen Germany Vector Institute for Artificial Intelligence Toronto Canada Chemical Physics Theory Group Department of Chemistry University of Toronto Canada Toronto Canada

We provide an integration of the universal, perturbative explicitly correlated [2]R12-correction in the context of the Variational Quantum Eigensolver (VQE). This approach is able to increase the accuracy of the underlying reference method significantly while requiring no additional quantum resources. The proposed approach only requires knowledge of the one- and two-particle reduced density matrices (RDMs) of the reference wavefunction;these can be measured after having reached convergence in the VQE. This computation comes at a cost that scales as the sixth power of the number of electrons. We explore the performance of the VQE+[2]R12approach using both conventional Gaussian basis sets and our recently proposed directly determined pair-natural orbitals obtained by multiresolution analysis (MRA-PNOs). Both Gaussian orbital and PNOs are investigated as a potential set of complementary basis functions in the computation of [2]R12. In particular the combination of MRA-PNOs with [2]R12has turned out to be very promising - persistently throughout our data, this allowed very accurate simulations at a quantum cost of a minimal basis set. Additionally, we found that the deployment of PNOs as complementary basis can greatly reduce the number of complementary basis functions that enter the computation of the correction at a complexity. Copyright © 2021, The Authors. All rights reserved.

关键词： Functions

Generative AI Enables Medical Image Segmentation in Ultra Low-Data Regimes

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Li Jindal, Basu Alaa, Ahmed Weinreb, Robert Wilson, David Segal, Eran Zou, James Xie, Pengtao Department of Electrical and Computer Engineering University of California La Jolla San DiegoCA United States Bakar Computational Health Sciences Institute University of California San Francisco San FranciscoCA United States Department of Electrical Engineering and Computer Sciences University of California Berkeley BerkeleyCA United States Hamilton Glaucoma Center Shiley Eye Institute Viterbi Family Department of Ophthalmology University of California La Jolla San DiegoCA United States Division of Pulmonary Allergy and Critical Care Medicine Department of Medicine University of Pittsburgh PittsburghPA United States Department of Computer Science and Applied Mathematics Weizmann Institute of Science Rehovot Israel Department of Molecular Cell Biology Weizmann Institute of Science Rehovot Israel Department of Biomedical Data Science Stanford University School of Medicine StanfordCA United States Department of Computer Science Stanford University StanfordCA United States Department of Medicine University of California La Jolla San DiegoCA United States

Semantic segmentation of medical images is pivotal in applications like disease diagnosis and treatment planning. While deep learning has excelled in automating this task, a major hurdle is the need for numerous annotated segmentation masks, which are resource-intensive to produce due to the required expertise and time. This scenario often leads to ultra low-data regimes, where annotated images are extremely limited, posing significant challenges for the generalization of conventional deep learning methods on test images. To address this, we introduce a generative deep learning framework, which uniquely generates high-quality paired segmentation masks and medical images, serving as auxiliary data for training robust models in data-scarce environments. Unlike traditional generative models that treat data generation and segmentation model training as separate processes, our method employs multi-level optimization for end-to-end data generation. This approach allows segmentation performance to directly influence the data generation process, ensuring that the generated data is specifically tailored to enhance the performance of the segmentation model. Our method demonstrated strong generalization performance across 9 diverse medical image segmentation tasks and on 16 datasets, in ultra-low data regimes, spanning various diseases, organs, and imaging modalities. When applied to various segmentation models, it achieved performance improvements of 10-20% (absolute), in both same-domain and out-of-domain scenarios. Notably, it requires 8 to 20 times less training data than existing methods to achieve comparable results. This advancement significantly improves the feasibility and cost-effectiveness of applying deep learning in medical imaging, particularly in scenarios with limited data availability. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

On the theoretical foundation of overset grid methods for hyperbolic problems: Well-posedness and conservation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Kopriva, David A. Nordström, Jan Gassner, Gregor J. Department of Mathematics The Florida State University TallahasseeFL32306 United States Computational Science Research Center San Diego State University San DiegoCA United States Department of Mathematics Applied Mathematics Linköping University Linköping581 83 Sweden Department of Mathematics and Applied Mathematics University of Johannesburg P.O. Box 524 Auckland Park2006 South Africa Department for Mathematics and Computer Science Center for Data and Simulation Science University of Cologne Weyertal 86-90 Cologne50931 Germany

We use the energy method to study the well-posedness of initial-boundary value problems approximated by overset mesh methods in one and two space dimensions for linear constant-coefficient hyperbolic systems. We show that in one space dimension, for both scalar equations and systems of equations, the problem where one domain partially oversets another is well-posed when characteristic coupling conditions are used. If a system cannot be diagonalized, as is ususally the case in multiple space dimensions, then the energy method does not give proper bounds in terms of initial and boundary data. For those problems, we propose a novel penalty approach. We show, by using a global energy that accounts for the energy in the overlap region of the domains, that under well-defined conditions on the coupling matrices the penalized overset domain problems are energy bounded, conservative, well-posed and have solutions equivalent to the original single domain problem. Copyright © 2021, The Authors. All rights reserved.

关键词： Constrained optimization

Comparisons of improved genomic predictions generated by different imputation methods for genotyping by sequencing data in livestock populations

学校读者我要写书评

暂无评论

Journal of Animal science and Biotechnology 2020年第2期11卷 316-326页

作者： Xiao Wang Guosheng Su Dan Hao Mogens SandøLund Haja N.Kadarmideen Quantitative Genomics Bioinformatics and Computational Biology GroupDepartment of Applied Mathematics and Computer ScienceTechnical University of DenmarkRichard Peterson PladsBuilding 3242800 Kongens LyngbyDenmark Center for Quantitative Genetics and Genomics Department of Molecular Biology and GeneticsAarhus University8830 TjeleDenmark Department of Molecular Biology and Genetics Aarhus University8000 Aarhus CDenmark College of Animal Science and Technology Northwest A&F UniversityYangling 712100ShannxiChina

Background:Genotyping by sequencing(GBS)still has problems with missing *** is important for using GBS for genomic predictions,especially for low depths,due to the large number of missing *** allele frequency(MAF)is widely used as a marker data editing criteria for genomic *** this study,three imputation methods(Beagle,IMPUTE2 and FImpute software)based on four MAF editing criteria were investigated with regard to imputation accuracy of missing genotypes and accuracy of genomic predictions,based on simulated data of livestock ***:Four MAFs(no MAF limit,MAF≥0.001,MAF≥0.01 and MAF≥0.03)were used for editing marker data before ***,IMPUTE2 and FImpute software were applied to impute the original ***,IMPUTE2 also imputed the expected genotype dosage after genotype correction(GcIM).The reliability of genomic predictions was calculated using GBS and imputed GBS *** results showed that imputation accuracies were the same for the three imputation methods,except for the data of sequencing read depth(depth)=2,where FImpute had a slightly lower imputation accuracy than Beagle and *** was observed to be the best for all of the imputations at depth=4,5 and 10,but the worst for depth=*** genomic prediction,retaining more SNPs with no MAF limit resulted in higher *** the depth increased to 10,the prediction reliabilities approached those using true genotypes in the GBS *** and IMPUTE2 had the largest increases in prediction reliability of 5 percentage points,and FImpute gained 3 percentage points at depth=*** best prediction was observed at depth=4,5 and 10 using GcIM,but the worst prediction was also observed using GcIM at depth=***:The current study showed that imputation accuracies were relatively low for GBS with low depths and high for GBS with high *** resulted in larger gains in the reliability of genomic predictions for GBS with lowe

关键词： Genomic prediction Genotyping by sequencing Imputation MAF Simulation

Multilevel approximation of Gaussian random fields: Covariance compression, estimation and spatial prediction

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Harbrecht, Helmut Herrmann, Lukas Kirchner, Kristin Schwab, Christoph Department of Mathematics and Computer Science University of Basel Spiegelgasse 1 Basel4051 Switzerland Johann Radon Institute for Computational and Applied Mathematics Austrian Academy of Sciences Altenbergerstrasse 69 Linz4040 Austria Delft Institute of Applied Mathematics Delft University of Technology P.O. Box 5031 Delft2600 GA Netherlands Seminar for Applied Mathematics ETH Zürich Rämistrasse 101 ZürichCH-8092 Switzerland

Centered Gaussian random fields (GRFs) indexed by compacta such as smooth, bounded domains in Euclidean space or smooth, compact and orientable manifolds are determined by their covariance operators. We consider centered GRFs given sample-wise as variational solutions to coloring operator equations driven by spatial white noise, with pseudodifferential coloring operator being elliptic, self-adjoint and positive from the Hörmander class. This includes the Matérn class of GRFs as a special case. Using microlocal tools and biorthogonal multiresolution analyses on the manifold, we prove that the precision and covariance operators, respectively, may be identified with bi-infinite matrices and finite sections may be diagonally preconditioned rendering the condition number independent of the dimension p of this section. We prove that a tapering strategy by thresholding as e.g. in [Bickel, P.J. and Levina, E. Covariance regularization by thresholding, Ann. Statist., 36 (2008), 2577–2604] applied on finite sections of the bi-infinite precision and covariance matrices results in optimally numerically sparse approximations. Numerical sparsity signifies that only asymptotically linearly many nonzero matrix entries are sufficient to approximate the original section of the bi-infinite covariance or precision matrix using this tapering strategy to arbitrary precision. This tapering strategy is non-adaptive and the locations of these nonzero matrix entries are known a priori. The tapered covariance or precision matrices may also be optimally diagonal preconditioned. Analysis of the relative size of the entries of the tapered covariance matrices motivates novel, multilevel Monte Carlo (MLMC) oracles for covariance estimation, in sample complexity that scales log-linearly with respect to the number p of parameters. This extends [Bickel, P.J. and Levina, E. Regularized Estimation of Large Covariance Matrices, Ann. Stat., 36 (2008), pp. 199–227] to estimation of (finite sections of) ps

关键词： Kriging