A paper from the Mathematical Optimization Laboratory (Prof. IIDUKA Hideaki), Department of Computer Science, School of Science and Technology, Meiji University, has been accepted to the 42nd Conference on Uncertainty in Artificial Intelligence (UAI2026), one of the top conferences in the field of machine learning.
Dates: Aug 17 - Aug 21, 2026
Venue: Amsterdam, the Netherlands
Authors: Ryusei Yamada, Naoki Sato, Hideaki Iiduka
Paper Title: Vanilla SGD with Momentum Survives Heavy-Tailed Noise: Convergence Analysis without Gradient Clipping or Normalization
≪
Japanese version≫
