Showing stat.MLShow all
3 papers · 1 filter
stat.ML2026
Spectrum-Adaptive Generalization Bounds for Trained Deep Transformers
Mana Sakai, Masaaki Imaizumi
Understanding why trained Transformers generalize well is a fundamental problem in modern machine learning theory, and complexity-based generalization bounds provide a principled w…
stat.ML2026
High-Dimensional Limit of Stochastic Gradient Flow via Dynamical Mean-Field Theory
Sota Nishiyama, Masaaki Imaizumi
Modern machine learning models are typically trained via multi-pass stochastic gradient descent (SGD) with small batch sizes, and understanding their dynamics in high dimensions is…
stat.ML2025
Precise Dynamics of Diagonal Linear Networks: A Unifying Analysis by Dynamical Mean-Field Theory
Sota Nishiyama, Masaaki Imaizumi
Diagonal linear networks (DLNs) are a tractable model that captures several nontrivial behaviors in neural network training, such as initialization-dependent solutions and incremen…