Is RL fine-tuning harder than regression? A PDE learning approach for diffusion models

Documenti analoghi

• Statistical guarantees for continuous-time policy evaluation: blessing of ellipticity and new tradeoffs
  di: Mou, Wenlong
  Pubblicazione: (2025)
• Continuous-time reinforcement learning: ellipticity enables model-free value function approximation
  di: Mou, Wenlong
  Pubblicazione: (2026)
• Optimal and instance-dependent guarantees for Markovian linear stochastic approximation
  di: Mou, Wenlong, et al.
  Pubblicazione: (2021)
• New algorithms for sampling and diffusion models
  di: Zhang, Xicheng
  Pubblicazione: (2024)
• A Piecewise Lyapunov Analysis of Sub-quadratic SGD: Applications to Robust and Quantile Regression
  di: Zhang, Yixuan, et al.
  Pubblicazione: (2025)