咨询与建议

限定检索结果

文献类型

  • 3 篇 期刊文献
  • 1 篇 会议

馆藏范围

  • 4 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 3 篇 理学
    • 3 篇 数学
  • 3 篇 工学
    • 3 篇 计算机科学与技术...
    • 1 篇 控制科学与工程
    • 1 篇 软件工程
  • 2 篇 管理学
    • 2 篇 管理科学与工程(可...

主题

  • 4 篇 data-driven algo...
  • 2 篇 automated algori...
  • 2 篇 machine learning
  • 1 篇 machine learning...
  • 1 篇 mechanism design
  • 1 篇 metalearning
  • 1 篇 optimization
  • 1 篇 adversarial mach...
  • 1 篇 nearest-neighbor...
  • 1 篇 numerical analys...
  • 1 篇 automated algori...
  • 1 篇 strategic classi...
  • 1 篇 runge-kutta meth...
  • 1 篇 computational bi...
  • 1 篇 newton-krylov so...
  • 1 篇 abstention

机构

  • 1 篇 univ texas el pa...
  • 1 篇 johns hopkins un...
  • 1 篇 department of co...
  • 1 篇 toyota technolog...
  • 1 篇 ocean genom inc ...
  • 1 篇 tech univ munich...
  • 1 篇 carnegie mellon ...
  • 1 篇 department of co...
  • 1 篇 inst energy & cl...
  • 1 篇 optimized market...
  • 1 篇 university of wa...
  • 1 篇 carnegie mellon ...
  • 1 篇 natl univ singap...
  • 1 篇 rhein westfal th...
  • 1 篇 univ penn philad...
  • 1 篇 strategy robot i...
  • 1 篇 strateg machine ...

作者

  • 1 篇 kingsford carl
  • 1 篇 li qianxiao
  • 1 篇 dick travis
  • 1 篇 deblasio dan
  • 1 篇 dietrich felix
  • 1 篇 kevrekidis ioann...
  • 1 篇 avrim blum
  • 1 篇 vitercik ellen
  • 1 篇 maria-florina ba...
  • 1 篇 hongyang zhang
  • 1 篇 dravyansh sharma
  • 1 篇 guo yue
  • 1 篇 sandholm tuomas
  • 1 篇 dahmen manuel
  • 1 篇 doncevic danimir...
  • 1 篇 mitsos alexander
  • 1 篇 xin yao
  • 1 篇 ke tang
  • 1 篇 balcan maria-flo...

语言

  • 4 篇 英文
检索条件"主题词=data-driven algorithm design"
4 条 记 录,以下是1-10 订阅
排序:
How Much data Is Sufficient to Learn High-Performing algorithms? Generalization Guarantees for data-driven algorithm design  2021
How Much Data Is Sufficient to Learn High-Performing Algorit...
收藏 引用
53rd Annual ACM SIGACT Symposium on Theory of Computing (STOC)
作者: Balcan, Maria-Florina DeBlasio, Dan Dick, Travis Kingsford, Carl Sandholm, Tuomas Vitercik, Ellen Carnegie Mellon Univ Pittsburgh PA 15213 USA Univ Texas El Paso El Paso TX 79968 USA Univ Penn Philadelphia PA 19104 USA Ocean Genom Inc Pittsburgh PA USA Strateg Machine Inc Pittsburgh PA USA Strategy Robot Inc Pittsburgh PA USA Optimized Markets Inc Pittsburgh PA USA
algorithms often have tunable parameters that impact performance metrics such as runtime and solution quality. For many algorithms used in practice, no parameter settings admit meaningful worst-case bounds, so the par... 详细信息
来源: 评论
Learn to optimize——a brief overview
收藏 引用
National Science Review 2024年 第8期11卷 39-47页
作者: Ke Tang Xin Yao Department of Computer Science and Engineering Southern University of Science and Technology Department of Computing and Decision Sciences Lingnan University
Most optimization problems of practical significance are typically solved by highly configurable parameterized *** achieve the best performance on a problem instance,a trial-and-error configuration process is required... 详细信息
来源: 评论
A RECURSIVELY RECURRENT NEURAL NETWORK (R2N2) ARCHITECTURE FOR LEARNING ITERATIVE algorithmS
收藏 引用
SIAM JOURNAL ON SCIENTIFIC COMPUTING 2024年 第2期46卷 A719-A743页
作者: Doncevic, Danimir T. Mitsos, Alexander Guo, Yue Li, Qianxiao Dietrich, Felix Dahmen, Manuel Kevrekidis, Ioannis G. Inst Energy & Climate Res Inst Energy & Climate Res Energy Syst Engn IEK 10 D-52425 Julich Germany Rhein Westfal TH Aachen Proc Syst Engn AVT SVT D-52074 Aachen Germany Natl Univ Singapore Dept Math Singapore 117543 Singapore Tech Univ Munich Dept Informat Boltzmannstr 3 D-85748 Garching Germany Inst Energy & Climate Res Inst Energy & Climate Res Energy Syst Engn IEK 10 D-52425 Julich Germany Johns Hopkins Univ Dept Appl Math & Stat & Chem & Biomol Engn Baltimore MD 21218 USA
Metalearning of numerical algorithms for a given task consists of the data -driven identification and adaptation of an algorithmic structure and the associated hyperparameters. To limit the complexity of the metalearn... 详细信息
来源: 评论
An analysis of robustness of non-Lipschitz networks
The Journal of Machine Learning Research
收藏 引用
The Journal of Machine Learning Research 2023年 第1期24卷 4548-4590页
作者: Maria-Florina Balcan Avrim Blum Dravyansh Sharma Hongyang Zhang Carnegie Mellon University Pittsburgh PA Toyota Technological Institute at Chicago Chicago IL University of Waterloo Waterloo ON Canada
Despite significant advances, deep networks remain highly susceptible to adversarial attack. One fundamental challenge is that small input perturbations can often produce large movements in the network's final-lay... 详细信息
来源: 评论