Results 11 to 20 of about 12,020,063 (274)
Accelerated Gossip via Stochastic Heavy Ball Method [PDF]
2018 56th Annual Allerton Conference on Communication, Control, and Computing (Allerton), 2018 8 pages, 5 Figures, 56th Annual Allerton Conference on Communication, Control, and Computing ...
Nicolas Loizou, Peter Richtárik
core +6 more sources
Linearly convergent stochastic heavy ball method for minimizing generalization error
CoRR, 2017 NIPS 2017, Workshop on Optimization for Machine Learning (camera ready version)
Nicolas Loizou, Peter Richtárik
openaire +3 more sources
Computer Research and Modeling, 2022 First-order optimization methods are workhorses in a wide range of modern applications in economics, physics, biology, machine learning, control, and other fields.
Marina Yuryevna Danilova +1 more
openaire +2 more sources
Universal heavy-ball method for nonconvex optimization under Hölder continuous Hessians
Mathematical ProgrammingAbstract We propose a new first-order method for minimizing nonconvex functions with Lipschitz continuous gradients and Hölder continuous Hessians. The proposed algorithm is a heavy-ball method equipped with two particular restart mechanisms.
Naoki Marumo
exaly +3 more sources
Adaptive Heavy-Ball Momentum Method Based on AdaGrad+ and Its Optimal Individual Convergence [PDF]
Jisuanji kexue, 2023 Adaptive strategies and momentum methods are commonly used to improve the performance of optimization algorithms.Most of the adaptive gradient methods use the AdaGrad-type strategy at present.The AdaGrad+ method,which is more suitable for dealing with ...
WEI Hongxu, LONG Sheng, TAO Wei, TAO Qing
doaj +1 more source
Hybrid Heavy-Ball Systems: Reset Methods for Optimization with Uncertainty [PDF]
2021 American Control Conference (ACC), 2021 Momentum methods for convex optimization often rely on precise choices of algorithmic parameters, based on knowledge of problem parameters, in order to achieve fast convergence, as well as to prevent oscillations that could severely restrict applications of these algorithms to cyber-physical systems.
Justin H. Le, Andrew R. Teel
openaire +2 more sources
Heavy-Ball-Based Hard Thresholding Pursuit for Sparse Phase Retrieval Problems
Mathematics, 2023 We introduce a novel iterative algorithm, termed the Heavy-Ball-Based Hard Thresholding Pursuit for sparse phase retrieval problem (SPR-HBHTP), to reconstruct a sparse signal from a small number of magnitude-only measurements.
Yingying Li +3 more
doaj +1 more source
A Study of Diagnostic Signatures of a Deep Groove Ball Bearing Based on a Nonlinear Dynamic Mode [PDF]
, 2015 For accurate fault detection and diagnosis, this paper focuses on the study of bearing vibration responses under increasing radial clearances due to investable wear and different bearing grades.
Gu, Fengshou +8 more
core +4 more sources
Calcium-Mechanochemistry Enabled Ketone Synthesis From Organic Iodides and Carboxylic Acids. [PDF]
Adv Sci (Weinh)Mechanochemically generated organocalcium species display unusual chemoselectivity toward carboxylates, enabling direct ketone synthesis without overaddition. Ball milling activates commercial calcium metal under ambient, solvent‐minimized conditions, providing a broad substrate scope, high functional‐group tolerance, and a practical one‐step ...
Pei M +9 more
europepmc +2 more sources
Measurement + Control, 2023 Due to extreme operating conditions such as high-speed and heavy loads, ball screws are prone to damages, that affect the accuracy and operational safety of the mechanical equipment.
Zhijie Xie +6 more
doaj +1 more source