Ngā tūemi rite

• Improved Convergence Rates of Muon Optimizer for Nonconvex Optimization
  mā: Nagashima, Shuntaro, me ētahi atu.
  I whakaputaina: (2026)
• Increasing Batch Size Improves Convergence of Stochastic Gradient Descent with Momentum
  mā: Kamo, Keisuke, me ētahi atu.
  I whakaputaina: (2025)
• Faster Convergence of Riemannian Stochastic Gradient Descent with Increasing Batch Size
  mā: Oowada, Kanata, me ētahi atu.
  I whakaputaina: (2025)
• Explicit and Implicit Graduated Optimization in Deep Neural Networks
  mā: Sato, Naoki, me ētahi atu.
  I whakaputaina: (2024)
• Using Stochastic Gradient Descent to Smooth Nonconvex Functions: Analysis of Implicit Graduated Optimization
  mā: Sato, Naoki, me ētahi atu.
  I whakaputaina: (2023)