Principled Curriculum Learning using Parameter Continuation Methods
Not on the map. Why?
Abstract (arXiv)
In this work, we propose a parameter continuation method for the optimization of neural networks. There is a close connection between parameter continuation, homotopies, and curriculum learning. The methods we propose here are theoretically justified and practically effective for several problems in deep neural networks. In particular, we demonstrate better generalization performance than state-of-the-art optimization techniques such as ADAM for supervised and unsupervised learning tasks.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 11 of its 36 references that are in the map. First posted on arXiv 29 Jul 2025.
Builds on
11 of 36 references.
References · 11
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
- 2019On The Power of Curriculum Learning in Training Deep Networkscited by 286
- 2021Curriculum Learning: A Surveycited by 259
- 2019Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutionscited by 192
- 2018Curriculum Learning by Transfer Learning: Theory and Experiments with Deep Networkscited by 114
- 2016Noisy Activation Functionscited by 53
- 2017Curriculum Dropoutcited by 50
- 2018Efficient Super Resolution For Large-Scale Images Using Attentional GANcited by 3
- 2024Rethinking the Relationship between Recurrent and Non-Recurrent Neural Networks: A Study in Sparsitycited by 3
- 2025Solo Connection: A Parameter Efficient Fine-Tuning Technique for Transformerscited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.