ASD+M: automatic parameter tuning in stochastic optimization and on-line learning

DOI10.1016/j.neunet.2017.07.007zbMath1434.68527OpenAlexW2751504024WikidataQ47672110 ScholiaQ47672110MaRDI QIDQ2179079

Paweł Wawrzyński

Publication date: 12 May 2020

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.neunet.2017.07.007

zbMATH Keywords

online learningstochastic gradient descentdeep learninglearning ratestep-sizeclassic momentum

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Stochastic programming (90C15)

Related Items (1)

ASD+M

Uses Software

• UCI-ml
• darch
• SGD-QN

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• An optimal method for stochastic composite optimization
• Autonomous reinforcement learning with experience replay
• Adaptive stepsizes for recursive estimation with applications in approximate dynamic programming
• Steepest descent with momentum for quadratic functions is a version of the conjugate gradient method
• Reducing the Dimensionality of Data with Neural Networks
• Some methods of speeding up the convergence of iteration methods
• A Stochastic Approximation Method

This page was built for publication: ASD+M: automatic parameter tuning in stochastic optimization and on-line learning