Stable Thompson Sampling: Valid Inference via Variance Inflation

Documenti analoghi

• Stability and Robustness via Regularization: Bandit Inference via Regularized Stochastic Mirror Descent
  di: Halder, Budhaditya, et al.
  Pubblicazione: (2026)
• Avoiding the Price of Adaptivity: Inference in Linear Contextual Bandits via Stability
  di: Praharaj, Samya, et al.
  Pubblicazione: (2025)
• Stochastic Optimization with Constraints: A Non-asymptotic Instance-Dependent Analysis
  di: Khamaru, Koulik
  Pubblicazione: (2024)
• Inference with the Upper Confidence Bound Algorithm
  di: Khamaru, Koulik, et al.
  Pubblicazione: (2024)
• On Instability of Minimax Optimal Optimism-Based Bandit Algorithms
  di: Praharaj, Samya, et al.
  Pubblicazione: (2025)