scientific article; zbMATH DE number 7626715
From MaRDI portal
Publication:5053185
No author found.
Publication date: 6 December 2022
Full work available at URL: https://arxiv.org/abs/2009.03831
Title: zbMATH Open Web Interface contents unavailable due to conflicting licenses.
online learningregret minimizationfollow the regularized leaderBlackwell's approachabilityglobal costs
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Primal-dual subgradient methods for convex problems
- Consistency and cautious fictitious play
- An analog of the minimax theorem for vector payoffs
- Improved algorithms for online load balancing
- Regret minimization in repeated matrix games with variable stage duration
- A primal-dual perspective of online learning algorithms
- Optimal strategies in repeated games with incomplete information
- Calibrated learning and correlated equilibrium
- Conditional universal consistency.
- Exponential weight approachability, applications to calibration and regret minimization
- Approachability, regret and calibration: implications and equivalences
- Efficient algorithms for online decision problems
- Sequential decision making with vector outcomes
- Online Learning and Online Convex Optimization
- The Well-Calibrated Bayesian
- Asymptotic calibration
- A Simple Adaptive Procedure Leading to Correlated Equilibrium
- Online and Random-order Load Balancing Simultaneously
- 10.1162/1532443041424328
- Online load balancing of temporary tasks
- Prediction, Learning, and Games
- Learning Theory
- Convex Analysis
- Internal regret in on-line portfolio selection
- A general class of adaptive strategies
- General convergence results for linear discriminant updates
- Relative loss bounds for multidimensional regression problems
