Dimensionality-induced information loss of outliers in deep neural networks

Documenti analoghi

• Approximation and Estimation Ability of Transformers for Sequence-to-Sequence Functions with Infinite Dimensional Input
  di: Takakura, Shokichi, et al.
  Pubblicazione: (2023)
• Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit
  di: Lee, Jason D., et al.
  Pubblicazione: (2024)
• Visualizing the loss landscapes of physics-informed neural networks
  di: Rowan, Conor, et al.
  Pubblicazione: (2026)
• Mamba Can Learn Low-Dimensional Targets In-Context via Test-Time Feature Learning
  di: Oh, Junsoo, et al.
  Pubblicazione: (2025)
• High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization
  di: Chen, Yihang, et al.
  Pubblicazione: (2024)