High-dimensional limit theorems for SGD: Momentum and Adaptive Step-sizes

Documenti analoghi

• Provable Benefits of Unsupervised Pre-training and Transfer Learning via Single-Index Models
  di: Jones-McCormick, Taj, et al.
  Pubblicazione: (2025)
• Detecting Metastable Basins in High Dimensions via Marginal Trajectory Distribution Discrimination
  di: Jones-McCormick, Taj
  Pubblicazione: (2026)
• Universality of high-dimensional scaling limits of stochastic gradient descent
  di: Gheissari, Reza, et al.
  Pubblicazione: (2025)
• Optimality of Message-Passing Architectures for Sparse Graphs
  di: Baranwal, Aseem, et al.
  Pubblicazione: (2023)
• Spectral alignment of stochastic gradient descent for high-dimensional classification tasks
  di: Arous, Gerard Ben, et al.
  Pubblicazione: (2023)