Showing 2025Show all
2 papers · 1 filter
cs.LG2025
Convergence Analysis of SGD under Expected Smoothness
Yuta Kawamoto, Hideaki Iiduka
Stochastic gradient descent (SGD) is the workhorse of large-scale learning, yet classical analyses rely on assumptions that can be either too strong (bounded variance) or too coars…
cs.LG2025
Convergence Bound and Critical Batch Size of Muon Optimizer
Naoki Sato, Hiroki Naganuma, Hideaki Iiduka
Muon, a recently proposed optimizer that leverages the inherent matrix structure of neural network parameters, has demonstrated strong empirical performance, indicating its potenti…