Distance-Aware Muon: Adaptive Step Scaling for Normalized Optimization

Documenti analoghi

• Streamlining in the Riemannian Realm: Efficient Riemannian Optimization with Loopless Variance Reduction
  di: Demidovich, Yury, et al.
  Pubblicazione: (2024)
• Randomized Feasibility Methods for Constrained Optimization with Adaptive Step Sizes
  di: Chakraborty, Abhishek, et al.
  Pubblicazione: (2026)
• MAST: Model-Agnostic Sparsified Training
  di: Demidovich, Yury, et al.
  Pubblicazione: (2023)
• Methods with Local Steps and Random Reshuffling for Generally Smooth Non-Convex Federated Optimization
  di: Demidovich, Yury, et al.
  Pubblicazione: (2024)
• Improved Convergence in Parameter-Agnostic Error Feedback through Momentum
  di: Sadiev, Abdurakhmon, et al.
  Pubblicazione: (2025)