Max Welling posts arXiv paper on symmetry breaking in networks

Max Welling at the University of Amsterdam posted the paper Spontaneous symmetry breaking and Goldstone modes for deep information propagation on arXiv on 14 May 2026. With co-authors Nabil Iqbal, Thomas Andy Keller, Takeru Miyato and Yue Song the work supplies analytic tools connecting spontaneous symmetry breaking to information propagation across layers in deep neural networks and examines implications for training dynamics.

Original post

MA

Max Welling#93@WELLINGMAX

We put the paper online that provides further details (beyond my ICLR keynote) on the role of spontaneous symmetry breaking and Goldstone modes in deep learning. Enjoy! (w/ Nabil Iqbal, Thomas Andy Keller, Takeru Miyato and Yue Song.) https://arxiv.org/abs/2605.14685

2:47 AM · May 15, 2026 View on X