Documenti analoghi

• Generalizability of Neural Networks Minimizing Empirical Risk Based on Expressive Ability
  di: Yu, Lijia, et al.
  Pubblicazione: (2025)
• Pessimism in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision Processes
  di: Lu, Miao, et al.
  Pubblicazione: (2022)
• Generalization Bound and New Algorithm for Clean-Label Backdoor Attack
  di: Yu, Lijia, et al.
  Pubblicazione: (2024)
• On the Provable Performance Guarantee of Efficient Reasoning Models
  di: Zeng, Hao, et al.
  Pubblicazione: (2025)
• Provable Reward-Agnostic Preference-Based Reinforcement Learning
  di: Zhan, Wenhao, et al.
  Pubblicazione: (2023)