A High Dimensional Statistical Model for Adversarial Training: Geometry and Trade-Offs

Documenti analoghi

• On the Geometry of Regularization in Adversarial Training: High-Dimensional Asymptotics and Generalization Bounds
  di: Vilucchio, Matteo, et al.
  Pubblicazione: (2024)
• Optimal Spectral Transitions in High-Dimensional Multi-Index Models
  di: Defilippis, Leonardo, et al.
  Pubblicazione: (2025)
• Deep Learning as Neural Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learning
  di: Dandi, Yatin, et al.
  Pubblicazione: (2026)
• On the existence of consistent adversarial attacks in high-dimensional linear classification
  di: Vilucchio, Matteo, et al.
  Pubblicazione: (2025)
• Asymptotics of SGD in Sequence-Single Index Models and Single-Layer Attention Networks
  di: Arnaboldi, Luca, et al.
  Pubblicazione: (2025)