On the Complexity of Learning Sparse Functions with Statistical and Gradient Queries

Documenti analoghi

• The merged-staircase property: a necessary and nearly sufficient condition for SGD learning of sparse functions on two-layer neural networks
  di: Abbe, Emmanuel, et al.
  Pubblicazione: (2022)
• Learning single-index models via harmonic decomposition
  di: Joshi, Nirmit, et al.
  Pubblicazione: (2025)
• Metalearning with Very Few Samples Per Task
  di: Aliakbarpour, Maryam, et al.
  Pubblicazione: (2023)
• Statistical Query Lower Bounds for Smoothed Agnostic Learning
  di: Diakonikolas, Ilias, et al.
  Pubblicazione: (2026)
• Statistical Query Lower Bounds for Learning Truncated Gaussians
  di: Diakonikolas, Ilias, et al.
  Pubblicazione: (2024)