Summary of Analyzing Neural Scaling Laws in Two-layer Networks with Power-law Data Spectra, by Roman Worschech and Bernd Rosenow
Analyzing Neural Scaling Laws in Two-Layer Networks with Power-Law Data Spectraby Roman Worschech, Bernd RosenowFirst…
Analyzing Neural Scaling Laws in Two-Layer Networks with Power-Law Data Spectraby Roman Worschech, Bernd RosenowFirst…
Scaling Laws Across Model Architectures: A Comparative Analysis of Dense and MoE Models in Large…
Searching for Efficient Linear Layers over a Continuous Space of Structured Matricesby Andres Potapczynski, Shikai…
Neural Scaling Laws of Deep ReLU and Deep Operator Network: A Theoretical Studyby Hao Liu,…
How Feature Learning Can Improve Neural Scaling Lawsby Blake Bordelon, Alexander Atanasov, Cengiz PehlevanFirst submitted…
Rethinking Conventional Wisdom in Machine Learning: From Generalization to Scalingby Lechao XiaoFirst submitted to arxiv…
Exploring Scaling Laws for Local SGD in Large Language Model Trainingby Qiaozhi He, Xiaomin Zhuang,…
Provable In-Context Learning of Linear Systems and Linear Elliptic PDEs with Transformersby Frank Cole, Yulong…
Scaling Law Hypothesis for Multimodal Modelby Qingyun Sun, Zhen Guo, PIN AI TeamFirst submitted to…
Safety vs. Performance: How Multi-Objective Learning Reduces Barriers to Market Entryby Meena Jagadeesan, Michael I. Jordan,…