Theoretical Foundation of Flow-Based Time Series Generation: Provable Approximation, Generalization, and Efficiency

Documenti analoghi

• Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond
  di: Ke, Yekun, et al.
  Pubblicazione: (2024)
• Unifying Learning Dynamics and Generalization in Transformers Scaling Law
  di: Yang, Chiwun
  Pubblicazione: (2025)
• Theoretical Guarantees for High Order Trajectory Refinement in Generative Flows
  di: Gong, Chengyue, et al.
  Pubblicazione: (2025)
• Video Latent Flow Matching: Optimal Polynomial Projections for Video Interpolation and Extrapolation
  di: Cao, Yang, et al.
  Pubblicazione: (2025)
• How Sparse Attention Approximates Exact Attention? Your Attention is Naturally $n^C$-Sparse
  di: Deng, Yichuan, et al.
  Pubblicazione: (2024)