Skip to main content

Research Repository

Advanced Search

Randomized block-coordinate adaptive algorithms for nonconvex optimization problems

Zhou, Yangfan; Huang, Kaizhu; Li, Jiang; Cheng, Cheng; Wang, Xuguang; Hussian, Amir; Liu, Xin


Yangfan Zhou

Kaizhu Huang

Jiang Li

Cheng Cheng

Xuguang Wang

Xin Liu


Nonconvex optimization problems have always been one focus in deep learning, in which many fast adaptive algorithms based on momentum are applied. However, the full gradient computation of high-dimensional feature vector in the above tasks become prohibitive. To reduce the computation cost for optimizers on nonconvex optimization problems typically seen in deep learning, this work proposes a randomized block-coordinate adaptive optimization algorithm, named RAda, which randomly picks a block from the full coordinates of the parameter vector and then sparsely computes its gradient. We prove that RAda converges to a -accurate solution with the stochastic first-order complexity of , where is the upper bound of the gradient’s square, under nonconvex cases. Experiments on public datasets including CIFAR-10, CIFAR-100, and Penn TreeBank, verify that RAda outperforms the other compared algorithms in terms of the computational cost.

Journal Article Type Article
Acceptance Date Feb 5, 2023
Online Publication Date Feb 11, 2023
Publication Date 2023-05
Deposit Date Feb 13, 2023
Publicly Available Date Feb 12, 2024
Journal Engineering Applications of Artificial Intelligence
Print ISSN 0952-1976
Publisher Elsevier
Peer Reviewed Peer Reviewed
Volume 121
Article Number 105968


Randomized Block-coordinate Adaptive Algorithms For Nonconvex Optimization Problems (accepted version) (849 Kb)

You might also like

Downloadable Citations