Calibration and Internal No-Regret with Random Signals

DOI10.1007/978-3-642-04414-4_10zbMath1262.91041OpenAlexW1571079074MaRDI QIDQ3648743

Vianney Perchet

Publication date: 1 December 2009

Published in: Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/978-3-642-04414-4_10

Mathematics Subject Classification ID

Signaling and communication in game theory (91A28)

Related Items

A general internal regret-free strategy ⋮ Approachability of convex sets in generalized quitting games ⋮ Learning in games with cumulative prospect theoretic preferences ⋮ Approachability of convex sets in games with partial monitoring ⋮ Approachability, regret and calibration: implications and equivalences ⋮ Approachability with constraints

Cites Work

• Unnamed Item
• An analog of the minimax theorem for vector payoffs
• A wide range no-regret theorem
• Regret in the on-line decision problem
• Conditional universal consistency.
• Minimizing regret: The general case
• Non-asymptotic calibration and resolution
• Weighted sums of certain dependent random variables
• Strategies for Prediction Under Imperfect Monitoring
• Asymptotic calibration
• A Simple Adaptive Procedure Leading to Correlated Equilibrium
• Probability Inequalities for Sums of Bounded Random Variables
• Prediction, Learning, and Games
• Calibration with Many Checking Rules
• Set-valued analysis