Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit

Documenti analoghi

• Pretrained transformer efficiently learns low-dimensional target functions in-context
  di: Oko, Kazusato, et al.
  Pubblicazione: (2024)
• Learning sum of diverse features: computational hardness and efficient gradient-based training for ridge combinations
  di: Oko, Kazusato, et al.
  Pubblicazione: (2024)
• Direct Distributional Optimization for Provable Alignment of Diffusion Models
  di: Kawata, Ryotaro, et al.
  Pubblicazione: (2025)
• Flow matching achieves almost minimax optimal convergence
  di: Fukumizu, Kenji, et al.
  Pubblicazione: (2024)
• Symmetric Mean-field Langevin Dynamics for Distributional Minimax Problems
  di: Kim, Juno, et al.
  Pubblicazione: (2023)