arXiv:2604. 00316v2 Announce Type: replace-cross Abstract: Grokking occurs when a model achieves high training accuracy but generalization to unseen test points happens long after that.
By Marcel Tom\`as Bernal, Neil Rohit Mallinar, Mikhail Belkin
arXiv:2604. 15613v4 Announce Type: replace-cross Abstract: We present Green-ELM, a non-iterative neural architecture that replaces gradient-based optimization of the output layer with a closed-form analytic solution over a fixed, high-dimensional random feature representation.
By Wladimir Silva
arXiv:2608. 14733v1 Announce Type: cross Abstract: Building on the foundation of single-hidden-layer neural networks, Fourier Feature Networks (FENs) are proposed, which incorporate Fourier features using $\cos$, $\sin$, or a combination of both.
By Qihong Yang, Zhijie Su, Yangtao Deng, Qiaolin He
arXiv:2506.11030v2 Announce Type: replace-cross
Abstract: Training neural networks has traditionally relied on backpropagation (BP), a gradient-based algorithm that, despite its widespread success, s...
By Nazmus Saadat As-Saquib, A N M Nafiz Abeer, Hung-Ta Chien, Byung-Jun Yoon, Suhas Kumar, Su-in Yi
arXiv:2311. 02960v5 Announce Type: replace Abstract: Over the past decade, deep learning has proven to be a highly effective tool for learning meaningful features from raw data.
By Peng Wang, Xiao Li, Can Yaras, Zhihui Zhu, Laura Balzano, Wei Hu, Qing Qu
arXiv:2606. 11319v1 Announce Type: new Abstract: Learning from imperfect data is a central theme in machine learning, connecting practical questions of robustness to fundamental questions of learnability.
By Justin Tahmassebpur, Asadullah Bhuiyan, Hyejin Kim, Omri Lesser