BSFA: Leveraging the Subspace Dichotomy to Accelerate Neural Network Training

Documenti analoghi

• Extra-Merge: Tracing the Rank-1 Subspace of Model Merging in Language Model Pre-Training
  di: Zhou, Wenjie, et al.
  Pubblicazione: (2026)
• When and Why Grouping Attention Heads Accelerates Muon Optimization
  di: Zhang, Hongtao, et al.
  Pubblicazione: (2026)
• The Stability of Singular Distribution: A Spectral Perspective on the Two-Phase Dynamics of Language Model Pre-training
  di: Zhang, Hongtao, et al.
  Pubblicazione: (2026)
• Training Bayesian Neural Networks with Sparse Subspace Variational Inference
  di: Li, Junbo, et al.
  Pubblicazione: (2024)
• Adversarial Training for Graph Neural Networks via Graph Subspace Energy Optimization
  di: Liu, Ganlin, et al.
  Pubblicazione: (2024)