A theoretical understanding of self-paced learning

DOI10.1016/j.ins.2017.05.043zbMath1435.68278OpenAlexW2620239873MaRDI QIDQ778415

Qian Zhao, Lu Jiang, De-Yu Meng

Publication date: 2 July 2020

Published in: Information Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.ins.2017.05.043

zbMATH Keywords

curriculum learningmultimedia event detectionnon-convex regularized penaltyself-paced learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (6)

Unnamed Item ⋮ Dual self-paced multi-view clustering ⋮ Leveraging prior-knowledge for weakly supervised object detection under a collaborative self-paced curriculum learning framework ⋮ On convergence properties of implicit self-paced objective ⋮ Robust sparse coding via self-paced learning for data representation ⋮ Unnamed Item

Uses Software

• ImageNet
• AlexNet

Cites Work

• Nearly unbiased variable selection under minimax concave penalty
• Optimal computational and statistical rates of convergence for sparse nonconvex learning problems
• Enhancing sparsity by reweighted \(\ell _{1}\) minimization
• Relaxed sparse eigenvalue conditions for sparse estimation via non-convex regularized regression
• Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
• 10.1162/153244303322753751
• Stochastic gradient boosting.
• A general theory of concave regularization for high-dimensional sparse estimation problems
• Unnamed Item
• Unnamed Item

This page was built for publication: A theoretical understanding of self-paced learning