Student-t processes as infinite-width limits of posterior Bayesian neural networks

Documenti analoghi

• Quantitative convergence of trained single layer neural networks to Gaussian processes
  di: Mosig, Eloy, et al.
  Pubblicazione: (2025)
• Large-width functional asymptotics for deep Gaussian neural networks
  di: Bracale, Daniele, et al.
  Pubblicazione: (2021)
• Large deviation principles for convolutional Bayesian neural networks
  di: Bassetti, Federico, et al.
  Pubblicazione: (2026)
• Exact full-RSB SAT/UNSAT transition in infinitely wide two-layer neural networks
  di: Annesi, Brandon L., et al.
  Pubblicazione: (2024)
• Proportional infinite-width infinite-depth limit for deep linear neural networks
  di: Bassetti, Federico, et al.
  Pubblicazione: (2024)