Feature Learning in Wide Neural Networks under $μ$P: Identifiability and Sparse-Dictionary Decomposition of the Mean-Field Limit

Documenti analoghi

• A functional Hungarian construction for sums of independent random variables
  di: Grama, Ion, et al.
  Pubblicazione: (2024)
• Limit theorems for compensated weighted sums and application to numerical approximations
  di: Liu, Yanghui
  Pubblicazione: (2024)
• Bilateral Gamma Approximation in Weiner Space
  di: Barman, Kalyan, et al.
  Pubblicazione: (2024)
• Note on the Weak Convergence of Hyperplane $α$-Quantile Functionals and Their Continuity in the Skorokhod J1 Topology
  di: Sparago, Pietro Maria
  Pubblicazione: (2026)
• Large and moderate deviations for Gaussian neural networks
  di: Macci, Claudio, et al.
  Pubblicazione: (2024)