Google scholar

Semantic scholar

Return to all papers.

Condensation

* indicates the corresponding author

#: Equal contribution

Condensation is a typical behavior of weights during the training when initialization is small. It is found when we study the phase diagram of neural networks, see Initialization.

[29] Hanxu Zhou, Qixuan Zhou, Zhenyuan Jin, Tao Luo, Yaoyu Zhang, Zhi-Qin John Xu*, Empirical Phase Diagram for Three-layer Neural Networks with Infinite Width. arxiv 2205.12101 (2022) pdf, and in arxiv, NeurIPS2022.

[18] Hanxu Zhou, Qixuan Zhou, Tao Luo, Yaoyu Zhang*, Zhi-Qin John Xu*, Towards Understanding the Condensation of Neural Networks at Initial Training. arxiv 2105.11686 (2021) pdf, and in arxiv, see slides and video talk in Chinese, NeurIPS2022.

[10] Tao Luo#, Zhi-Qin John Xu #, Zheng Ma, Yaoyu Zhang*, Phase diagram for two-layer ReLU neural networks at infinite-width limit, arxiv 2007.07497 (2020), Journal of Machine Learning Research (2021) pdf, and in arxiv