咨询与建议

限定检索结果

文献类型

  • 13 篇 期刊文献
  • 3 篇 会议

馆藏范围

  • 16 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 12 篇 工学
    • 9 篇 计算机科学与技术...
    • 5 篇 电气工程
    • 2 篇 材料科学与工程(可...
    • 2 篇 控制科学与工程
    • 2 篇 软件工程
    • 1 篇 信息与通信工程
    • 1 篇 核科学与技术
  • 5 篇 理学
    • 5 篇 数学
  • 5 篇 管理学
    • 5 篇 管理科学与工程(可...
  • 1 篇 医学
    • 1 篇 临床医学

主题

  • 16 篇 accelerated algo...
  • 3 篇 distributed opti...
  • 2 篇 proximal algorit...
  • 2 篇 convergence
  • 2 篇 sparse learning
  • 2 篇 optimization
  • 2 篇 iterative/recurs...
  • 2 篇 diffusion
  • 2 篇 estimation
  • 2 篇 monte carlo
  • 2 篇 lower bounds
  • 1 篇 phase transition...
  • 1 篇 underestimate se...
  • 1 篇 stochastic
  • 1 篇 productivity
  • 1 篇 computational co...
  • 1 篇 nonsmooth optimi...
  • 1 篇 load balancing
  • 1 篇 saddle-point pro...
  • 1 篇 geochemical appl...

机构

  • 2 篇 ras inst informa...
  • 2 篇 hse univ moscow
  • 1 篇 univ canterbury ...
  • 1 篇 jsc vniinm mosco...
  • 1 篇 department of el...
  • 1 篇 st petersburg st...
  • 1 篇 univ colorado bo...
  • 1 篇 univ bologna dep...
  • 1 篇 mohamed bin zaye...
  • 1 篇 issy les mouline...
  • 1 篇 univ michigan de...
  • 1 篇 politecn torino ...
  • 1 篇 univ canterbury ...
  • 1 篇 inst natl rech i...
  • 1 篇 st petersburg st...
  • 1 篇 moscow inst phys...
  • 1 篇 univ delaware de...
  • 1 篇 king abdullah un...
  • 1 篇 univ north texas...
  • 1 篇 rice univ housto...

作者

  • 2 篇 gasnikov alexand...
  • 2 篇 tappenden rachae...
  • 2 篇 takac martin
  • 2 篇 borodich ekateri...
  • 1 篇 diego regruto
  • 1 篇 regruto diego
  • 1 篇 chezhegov saveli...
  • 1 篇 nesterov yurii
  • 1 篇 sivak a. b.
  • 1 篇 ochoa daniel e.
  • 1 篇 lin claire yilin
  • 1 篇 perruchet c
  • 1 篇 doikov nikita
  • 1 篇 kovalev dmitry
  • 1 篇 vlachos dionisio...
  • 1 篇 kia solmaz s.
  • 1 篇 juditsky anatoli
  • 1 篇 sadiev abdurakhm...
  • 1 篇 fosson sophie m.
  • 1 篇 dvinskikh darina

语言

  • 14 篇 英文
  • 2 篇 其他
检索条件"主题词=accelerated algorithms"
16 条 记 录,以下是11-20 订阅
排序:
Decentralized personalized federated learning: Lower bounds and optimal algorithm for all personalization modes
收藏 引用
EURO JOURNAL ON COMPUTATIONAL OPTIMIZATION 2022年 10卷
作者: Sadiev, Abdurakhmon Borodich, Ekaterina Beznosikov, Aleksandr Dvinskikh, Darina Chezhegov, Saveliy Tappenden, Rachael Takac, Martin Gasnikov, Alexander Moscow Inst Phys & Technol MIPT Moscow Russia Mohamed Bin Zayed Univ Artificial Intelligence MB Abu Dhabi U Arab Emirates HSE Univ Moscow Russia Univ Canterbury Christchurch New Zealand RAS Inst Informat Transmiss Problems Moscow Russia
This paper considers the problem of decentralized, personal-ized federated learning. For centralized personalized federated learning, a penalty that measures the deviation from the local model and its average, is ofte... 详细信息
来源: 评论
accelerated variance-reduced methods for saddle-point problems
收藏 引用
EURO JOURNAL ON COMPUTATIONAL OPTIMIZATION 2022年 10卷
作者: Borodich, Ekaterina Tominin, Vladislav Tominin, Yaroslav Kovalev, Dmitry Gasnikov, Alexander Dvurechensky, Pavel Moscow Inst Phys & Technol Moscow Russia HSE Univ Moscow Russia Weierstrass Inst Appl Anal & Stochast Berlin Germany King Abdullah Univ Sci & Technol Thuwal Saudi Arabia RAS Inst Informat Transmiss Problems Moscow Russia
We consider composite minimax optimization problems where the goal is to find a saddle-point of a large sum of non -bilinear objective functions augmented by simple composite regularizers for the primal and dual varia... 详细信息
来源: 评论
Efficient Dynamic Parallel MRI Reconstruction for the Low-Rank Plus Sparse Model
收藏 引用
IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING 2019年 第1期5卷 17-26页
作者: Lin, Claire Yilin Fessler, Jeffrey A. Univ Michigan Dept Math Ann Arbor MI 48109 USA Univ Michigan Dept Elect Engn & Comp Sci Ann Arbor MI 48109 USA
The low-rank plus sparse (L+S) decomposition model enables the reconstruction of undersampled dynamic parallel magnetic resonance imaging data. Solving for the low rank and the sparse components involves nonsmooth com... 详细信息
来源: 评论
An overview of spatial microscopic and accelerated kinetic Monte Carlo methods
收藏 引用
JOURNAL OF COMPUTER-AIDED MATERIALS DESIGN 2007年 第2期14卷 253-308页
作者: Chatterjee, Abhijit Vlachos, Dionisios G. Univ Delaware Dept Chem Engn Newark DE 19716 USA Univ Delaware Ctr Catalyt Sci & Technol Newark DE 19716 USA
The microscopic spatial kinetic Monte Carlo (KMC) method has been employed extensively in materials modeling. In this review paper, we focus on different traditional and multiscale KMC algorithms, challenges associate... 详细信息
来源: 评论
accelerated STOCHASTIC APPROXIMATION
收藏 引用
SIAM JOURNAL ON OPTIMIZATION 1993年 第4期3卷 868-881页
作者: Delyon, Bernard Juditsky, Anatoli Inst Natl Rech Informat & Automat Inst Rech Informat & Syst Aleatoires F-35042 Rennes France
A technique to accelerate convergence of stochastic approximation algorithms is studied. It is based on Kesten's idea of equalization of the gain coefficient for the Robbins-Monro algorithm. Convergence with proba... 详细信息
来源: 评论
CONSTRAINED AGGLOMERATIVE HIERARCHICAL-CLASSIFICATION
收藏 引用
PATTERN RECOGNITION 1983年 第2期16卷 213-217页
作者: PERRUCHET, C Issy les Moulineaux France
This paper presents a method of classification taking account of a contiguity constraint. This procedure is applicable to all data sets represented in two distinct spaces, one of which is defined by the introduction o... 详细信息
来源: 评论