How Data Mixing Shapes In-Context Learning: Asymptotic Equivalence for Transformers with MLPs

Documenti analoghi

• Asymptotic Study of In-context Learning with Random Transformers through Equivalent Models
  di: Demir, Samet, et al.
  Pubblicazione: (2025)
• Asymptotic Analysis of Two-Layer Neural Networks after One Gradient Step under Gaussian Mixtures Data with Structure
  di: Demir, Samet, et al.
  Pubblicazione: (2025)
• Optimal Attention Temperature Improves the Robustness of In-Context Learning under Distribution Shift in High Dimensions
  di: Demir, Samet, et al.
  Pubblicazione: (2025)
• Learning Beyond the Gaussian Data: Learning Dynamics of Neural Networks on an Expressive and Cumulant-Controllable Data Model
  di: Ure, Onat, et al.
  Pubblicazione: (2026)
• Implicitly Normalized Online PCA: A Regularized Algorithm with Exact High-Dimensional Dynamics
  di: Demir, Samet, et al.
  Pubblicazione: (2025)