[2407.02827] Convergence of Implicit Gradient Descent for Training Two-Layer Physics-Informed Neural Networks

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. arXiv Operational Status Get status notifications via email or slack

[2407.02827] Convergence of Implicit Gradient Descent for Training Two-Layer Physics-Informed Neural Networks Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Machine Learning arXiv:2407.02827 (cs) [Submitted on 3 Jul 2024 ( v1 ), last revised 1 Aug 2025 (this version, v3)] Title: Convergence of Implicit Gradient Descent for Training Two-Layer Physics-Informed Neural Networks Authors: Xianliang Xu , Ting Du , Wang Kong , Bin Shan , Ye Li , Zhongyi Huang View a PDF of the paper title

related reading

• Some Math behind Neural Tangent Kernel | Lil'Loglilianweng.github.io
• nn-notes.pdfboris-hanin.github.io
• Why Momentum Really Worksdistill.pub
• The Little Book of Deep Learningfleuret.org
• NeurIPS-2021-understanding-end-to-end-model-based-reinforcement-learning-methods-as-implicit-parameterization-Supplemental.pdflis.csail.mit.edu
• Muon: An optimizer for hidden layers in neural networks | Keller Jordan blogkellerjordan.github.io
• Understanding Deep Learningudlbook.github.io
• CS231n Deep Learning for Computer Visioncs231n.github.io
• [2608.13335] Neural Quadratic Forms: A Unified Minimal Model for Sudden Learning and Scaling Lawsarxiv.org
• Understanding the Neural Tangent Kernel – EigenTaleseigentales.com
• Statistical Mechanics of Deep Learningganguli-gang.stanford.edu
• [2604.21691] There Will Be a Scientific Theory of Deep Learningarxiv.org