1412.0233
arxiv.org · 5,928 words · saved by 1 readers
N/A
The Loss Surfaces of Multilayer Networks Anna Choromanska Mikael Henaff Michael Mathieu Gérard Ben Arous Yann LeCun achoroma@cims.nyu.edu mbh305@nyu.edu mathieu@cs.nyu.edu benarous@cims.nyu.edu yann@cs.nyu.edu Courant Institute of Mathematical Sciences New York, NY, USA arXiv:1412.0233v3 [cs.LG] 21…
saved by
related reading
- Understanding deep learning requires rethinking generalizationarxiv.org
- nn-notes.pdfboris-hanin.github.io
- Neural Networks, Manifolds, and Topology -- colah's blogcolah.github.io
- Statistical Mechanics of Deep Learningganguli-gang.stanford.edu
- On_the_Spectral_Bias_of_Neural_Networks__ICML_ (3)proceedings.mlr.press
- NL.pdfabehrouz.github.io
- [2605.01172] A Theory of Generalization in Deep Learningarxiv.org
- [2608.13335] Neural Quadratic Forms: A Unified Minimal Model for Sudden Learning and Scaling Lawsarxiv.org
- arxiv.org/pdf/1805.08522arxiv.org
- [2604.21691] There Will Be a Scientific Theory of Deep Learningarxiv.org
- The Little Book of Deep Learningfleuret.org
- [2402.01258] Transformers Learn Nonlinear Features In Context: Nonconvex Mean-field Dynamics on the Attention Landscapearxiv.org