scientific article; zbMATH DE number 7626715

MaRDI QIDQ5053185zbMATH OpenFDO

Authors

Publication date 6 December 2022

Full work available at URL https://arxiv.org/abs/2009.03831, https://jmlr.csail.mit.edu/papers/v22/20-1019.html

zbMATH Keywords

Blackwell's approachabilityfollow the regularized leaderglobal costsonline learningregret minimization

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites work

• 10.1162/1532443041424328
• A general class of adaptive strategies
• A primal-dual perspective of online learning algorithms
• A Simple Adaptive Procedure Leading to Correlated Equilibrium
• An analog of the minimax theorem for vector payoffs
• An online convex optimization approach to Blackwell's approachability
• Approachability, regret and calibration: implications and equivalences
• Asymptotic calibration
• Calibrated learning and correlated equilibrium
• Conditional universal consistency.
• Consistency and cautious fictitious play
• Convex Analysis
• Efficient algorithms for online decision problems
• Exponential weight approachability, applications to calibration and regret minimization
• General convergence results for linear discriminant updates
• scientific article; zbMATH DE number 3122013 (Why is no real title available?)
• scientific article; zbMATH DE number 3128728 (Why is no real title available?)
• scientific article; zbMATH DE number 3177945 (Why is no real title available?)
• scientific article; zbMATH DE number 1232130 (Why is no real title available?)
• scientific article; zbMATH DE number 2107836 (Why is no real title available?)
• Improved algorithms for online load balancing
• Internal regret in on-line portfolio selection
• Learning permutations with exponential weights
• Learning Theory
• Online and Random-order Load Balancing Simultaneously
• Online learning and online convex optimization
• Online load balancing of temporary tasks
• Optimal strategies in repeated games with incomplete information
• Prediction, Learning, and Games
• Primal-dual subgradient methods for convex problems
• Randomized online PCA algorithms with regret bounds that are logarithmic in the dimension
• Regret minimization in repeated matrix games with variable stage duration
• Regularization techniques for learning with matrices
• Relative loss bounds for multidimensional regression problems
• Response-based approachability with applications to generalized no-regret problems
• Sequential decision making with vector outcomes
• The Well-Calibrated Bayesian

Cited in

(3)

• Approachability, regret and calibration: implications and equivalences
• Refined approachability algorithms and application to regret minimization with global costs
• Pseudonorm approachability and applications to regret minimization

This page was built for publication:

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5053185)