咨询与建议

限定检索结果

文献类型

  • 17 篇 期刊文献
  • 7 篇 会议

馆藏范围

  • 24 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 14 篇 理学
    • 7 篇 数学
    • 4 篇 物理学
    • 4 篇 统计学(可授理学、...
    • 3 篇 化学
    • 3 篇 生物学
    • 2 篇 系统科学
    • 1 篇 天文学
  • 14 篇 工学
    • 8 篇 计算机科学与技术...
    • 7 篇 软件工程
    • 3 篇 控制科学与工程
    • 3 篇 化学工程与技术
    • 3 篇 生物工程
    • 2 篇 材料科学与工程(可...
    • 1 篇 仪器科学与技术
    • 1 篇 信息与通信工程
    • 1 篇 安全科学与工程
  • 1 篇 法学
    • 1 篇 社会学
  • 1 篇 教育学
    • 1 篇 教育学
  • 1 篇 管理学
    • 1 篇 管理科学与工程(可...

主题

  • 2 篇 embeddings
  • 2 篇 convex optimizat...
  • 1 篇 chemical activat...
  • 1 篇 sustainable deve...
  • 1 篇 deep learning
  • 1 篇 bibliometrics
  • 1 篇 digital arithmet...
  • 1 篇 three-dimensiona...
  • 1 篇 percolation
  • 1 篇 transformers
  • 1 篇 electric field e...
  • 1 篇 education
  • 1 篇 iterative method...
  • 1 篇 polymer conforma...
  • 1 篇 prediction
  • 1 篇 capacitance
  • 1 篇 singular value d...
  • 1 篇 educational tech...
  • 1 篇 zebrafish cardio...
  • 1 篇 spatio-temporal ...

机构

  • 5 篇 machine learning...
  • 4 篇 machine learning...
  • 3 篇 school of comput...
  • 3 篇 school of inform...
  • 3 篇 key laboratory o...
  • 3 篇 key laboratory o...
  • 2 篇 cispa helmholtz ...
  • 2 篇 jiangsu province...
  • 1 篇 beijing national...
  • 1 篇 college of compu...
  • 1 篇 data analytics &...
  • 1 篇 department of ph...
  • 1 篇 yale university ...
  • 1 篇 laboratory of ma...
  • 1 篇 max planck insti...
  • 1 篇 institute of phy...
  • 1 篇 menten ai inc. p...
  • 1 篇 institute for th...
  • 1 篇 benin
  • 1 篇 icfo - institut ...

作者

  • 6 篇 jaggi martin
  • 5 篇 martin jaggi
  • 3 篇 sebastian u. sti...
  • 2 篇 nikita doikov
  • 2 篇 hossmann andreaa
  • 2 篇 bennani-smires k...
  • 2 篇 musat claudiu
  • 2 篇 baeriswyl michae...
  • 2 篇 li junke
  • 2 篇 liu kai
  • 1 篇 okula robert
  • 1 篇 brokowski trevor
  • 1 篇 lewenstein macie...
  • 1 篇 jun meng
  • 1 篇 raj anant
  • 1 篇 wang lei
  • 1 篇 stich sebastian ...
  • 1 篇 koch rouven
  • 1 篇 jan overbeck
  • 1 篇 carleo giuseppe

语言

  • 23 篇 英文
  • 1 篇 中文
检索条件"机构=Laboratory of Machine Learning and Optimization"
24 条 记 录,以下是1-10 订阅
排序:
Expanded Gating Ranges Improve Activation Functions
arXiv
收藏 引用
arXiv 2024年
作者: Huang, Allen Hao Machine Learning and Optimization Laboratory EPFL Switzerland
Activation functions are core components of all deep learning architectures. Currently, the most popular activation functions are smooth ReLU variants like GELU and SiLU. These are self-gated activation functions wher... 详细信息
来源: 评论
Beyond spectral gap: the role of the topology in decentralized learning
The Journal of Machine Learning Research
收藏 引用
The Journal of machine learning Research 2023年 第1期24卷 17074-17104页
作者: Thijs Vogels Hadrien Hendrikx Martin Jaggi Machine Learning and Optimization Laboratory EPFL Lausanne Switzerland
In data-parallel optimization of machine learning models, workers collaborate to improve their estimates of the model: more accurate gradients allow them to use larger learning rates and optimize faster. In the decent... 详细信息
来源: 评论
Beyond spectral gap (extended): The role of the topology in decentralized learning
arXiv
收藏 引用
arXiv 2023年
作者: Vogels, Thijs Hendrikx, Hadrien Jaggi, Martin Machine Learning and Optimization Laboratory EPFL Lausanne Switzerland
In data-parallel optimization of machine learning models, workers collaborate to improve their estimates of the model: more accurate gradients allow them to use larger learning rates and optimize faster. In the decent... 详细信息
来源: 评论
Second-Order optimization with Lazy Hessians
arXiv
收藏 引用
arXiv 2022年
作者: Doikov, Nikita Chayti, El Mahdi Jaggi, Martin Machine Learning and Optimization Laboratory EPFL Switzerland
We analyze Newton’s method with lazy Hessian updates for solving general possibly non-convex optimization problems. We propose to reuse a previously seen Hessian for several iterations while computing new gradients a... 详细信息
来源: 评论
Spectral preconditioning for gradient methods on graded non-convex functions  24
Spectral preconditioning for gradient methods on graded non-...
收藏 引用
Proceedings of the 41st International Conference on machine learning
作者: Nikita Doikov Sebastian U. Stich Martin Jaggi Machine Learning and Optimization Laboratory (MLO) EPFL Lausanne Switzerland CISPA Helmholtz Center for Information Security Saarbrücken Germany
The performance of optimization methods is often tied to the spectrum of the objective Hessian. Yet, conventional assumptions, such as smoothness, do often not enable us to make finely-grained convergence statements--...
来源: 评论
MEMORY EFFICIENT MIXED PRECISION OPTIMIZERS
arXiv
收藏 引用
arXiv 2023年
作者: Lewandowski, Basile Kosson, Atli Machine Learning Optimization laboratory École Polytechnique Fédérale de Lausanne Switzerland
Traditional optimization methods rely on the use of single-precision floating point arithmetic, which can be costly in terms of memory size and computing power. However, mixed precision optimization techniques leverag... 详细信息
来源: 评论
On convergence of incremental gradient for non-convex smooth functions  24
On convergence of incremental gradient for non-convex smooth...
收藏 引用
Proceedings of the 41st International Conference on machine learning
作者: Anastasia Koloskova Nikita Doikov Sebastian U. Stich Martin Jaggi Machine Learning and Optimization Laboratory (MLO) EPFL Lausanne Switzerland CISPA Helmholtz Center for Information Security Saarbrücken Germany
In machine learning and neural network optimization, algorithms like incremental gradient, and shuffle SGD are popular due to minimizing the number of cache misses and good practical convergence behavior. However, the...
来源: 评论
High-speed identification of suspended carbon nanotubes using Raman spectroscopy and deep learning
收藏 引用
Microsystems & Nanoengineering 2022年 第1期8卷 259-267页
作者: Jian Zhang Mickael L.Perrin Luis Barba Jan Overbeck Seoho Jung Brock Grassy Aryan Agal Rico Muff Rolf Brönnimann Miroslav Haluska Cosmin Roman Christofer Hierold Martin Jaggi Michel Calame Laboratory for Transport at Nanoscale Interfaces EmpaSwiss Federal Laboratories for Materials Science and TechnologyCH-8600 DübendorfSwitzerland Machine Learning and Optimization Laboratory School of Computer and Communication SciencesEPFLCH-1015 LausanneSwitzerland Department of Physics and Swiss Nanoscience Institute University of BaselCH-4056 BaselSwitzerland Micro-and Nanosystems Department of Mechanical and Process EngineeringETH ZurichCH-8092 ZurichSwitzerland
The identification of nanomaterials with the properties required for energy-efficient electronic systems is usually a tedious human task.A workflow to rapidly localize and characterize nanomaterials at the various sta... 详细信息
来源: 评论
PCT-Cap: Point Cloud Transformer for Accurate 3D Capacitance Extraction
PCT-Cap: Point Cloud Transformer for Accurate 3D Capacitance...
收藏 引用
Electronics Design Automation (ISEDA), International Symposium of
作者: Ye Cai Yuyao Liang Zhipeng Luo Biwei Xie Xingquan Li College of Computer Science and Software Engineering Shenzhen University Shenzhen China Peng Cheng Laboratory Shenzhen China Center of Machine Learning and Optimization Minnan Normal University Zhangzhou China State Key Lab of Processors Chinese Academy of Sciences Institute of Computing Technology Beijing China
Accurate parasitic capacitance extraction becomes increasingly essential in advanced technology nodes. 2.5D ex-traction requires more effort to maintain accuracy comparable to the 3D solver. In this work, two experime... 详细信息
来源: 评论
Analysis of the Research Status of Information Technology Education Literature in China and Abroad  24
Analysis of the Research Status of Information Technology Ed...
收藏 引用
24th IEEE International Conference on High Performance Computing and Communications, 8th IEEE International Conference on Data Science and Systems, 20th IEEE International Conference on Smart City and 8th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Application, HPCC/DSS/SmartCity/DependSys 2022
作者: Zhao, Yulin Liu, Kai Li, Junke School of Information Engineering Suqian University Jiangsu Suqian223800 China School of Computer and Information Qiannan Normal University for Nationalities Duyun558000 China Jiangsu Province Engineering Research Center of Smart Poultry Farming and Intelligent Equipment Jiangsu 223800 China Key Laboratory of Machine Learning and Unstructured Data Processing of Qiannan Duyun558000 China Key Laboratory of Complex Systems and Intelligent Optimization of Guizhou Duyun558000 China
Information technology education contributes to the development of national education. Understanding the research status of information technology education at home and abroad is helpful to the implementation of educa... 详细信息
来源: 评论