Suspicious Alignment of SGD: A Fine-Grained Step Size Condition Analysis

Documenti analoghi

• Depth, Not Data: An Analysis of Hessian Spectral Bifurcation
  di: Deng, Shenyang, et al.
  Pubblicazione: (2026)
• RMNP: Row-Momentum Normalized Preconditioning for Scalable Matrix-Based Optimization
  di: Deng, Shenyang, et al.
  Pubblicazione: (2026)
• Balancing Learning Rates Across Layers: Exact Two-Step Dynamics and Optimal Scaling in Linear Neural Networks
  di: Pang, Tianyu, et al.
  Pubblicazione: (2026)
• From Spikes to Heavy Tails: Unveiling the Spectral Evolution of Neural Networks
  di: Kothapalli, Vignesh, et al.
  Pubblicazione: (2024)
• Does SGD really happen in tiny subspaces?
  di: Song, Minhak, et al.
  Pubblicazione: (2024)