Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring

Documenti analoghi

• Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Analysis and Best-of-Both-Worlds
  di: Ito, Shinji, et al.
  Pubblicazione: (2024)
• Stability-penalty-adaptive follow-the-regularized-leader: Sparsity, game-dependency, and best-of-both-worlds
  di: Tsuchiya, Taira, et al.
  Pubblicazione: (2023)
• A Simple and Adaptive Learning Rate for FTRL in Online Learning with Minimax Regret of $Θ(T^{2/3})$ and its Application to Best-of-Both-Worlds
  di: Tsuchiya, Taira, et al.
  Pubblicazione: (2024)
• Adversarial Learning in Games with Bandit Feedback: Logarithmic Pure-Strategy Maximin Regret
  di: Ito, Shinji, et al.
  Pubblicazione: (2026)
• Fast Rates in Stochastic Online Convex Optimization by Exploiting the Curvature of Feasible Sets
  di: Tsuchiya, Taira, et al.
  Pubblicazione: (2024)