No-regret algorithms in on-line learning, games and convex optimization
From MaRDI portal
Publication:6120936
DOI10.1007/s10107-023-01927-7OpenAlexW4360610514MaRDI QIDQ6120936
Publication date: 21 February 2024
Published in: Mathematical Programming. Series A. Series B (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1007/s10107-023-01927-7
Analysis of algorithms (68W40) Convex programming (90C25) Learning and adaptive systems in artificial intelligence (68T05) Rationality and learning in game theory (91A26)
Cites Work
- Primal-dual subgradient methods for convex problems
- Finite composite games: equilibria and dynamics
- On the convergence of the iterates of the ``fast iterative shrinkage/thresholding algorithm
- A continuous-time approach to online optimization
- Consistency and cautious fictitious play
- Regularized Lotka-Volterra dynamical system as continuous proximal-like method in optimization.
- An analog of the minimax theorem for vector payoffs
- A descent algorithm for solving monotone variational inequalities and monotone complementarity problems
- Finite-dimensional variational inequality and nonlinear complementarity problems: A survey of theory, algorithms and applications
- Replicator dynamics: old and new
- Exponential weight algorithm in continuous time
- Projected subgradient methods with non-Euclidean distances for non-differentiable convex minimization and variational inequalities
- Asymptotic convergence of nonlinear contraction semigroups in Hilbert space
- Evolutionarily stable strategies and game dynamics
- Dynamical systems and variational inequalities
- Adjustment dynamics and rational play in games
- The weighted majority algorithm
- Calibrated learning and correlated equilibrium
- Potential-based algorithms in on-line prediction and game theory
- Regret-based continuous-time dynamics.
- Introductory lectures on convex optimization. A basic course.
- Riemannian game dynamics
- A simplified view of first order methods for optimization
- Learning in games with continuous action sets and unknown payoff functions
- Minmax via replicator dynamics
- A wide range no-regret theorem
- Mirror descent and nonlinear projected subgradient methods for convex optimization.
- Potential games
- Regret in the on-line decision problem
- Adaptive game playing using multiplicative weights
- Conditional universal consistency.
- No-regret dynamics and fictitious play
- Bregman forward-backward operator splitting
- Large population potential games
- On damped second-order gradient systems
- Forward-backward splitting with Bregman distances
- Fast convergence of inertial dynamics and algorithms with asymptotic vanishing viscosity
- Approachability, regret and calibration: implications and equivalences
- Best response dynamics for continuous zero-sum games
- The projection dynamic and the geometry of population games
- The projection dynamic and the replicator dynamic
- Efficient algorithms for online decision problems
- Learning in Games via Reinforcement and Regularization
- A Differential Equation for Modeling Nesterov's Accelerated Gradient Method: Theory and Insights
- Simple Adaptive Strategies
- Evolution equations for maximal monotone operators: asymptotic analysis in continuous and discrete time
- Online Learning and Online Convex Optimization
- Penalty-Regulated Dynamics and Robust Learning Procedures in Games
- A new mathematical framework for the study of linkage and selection
- Asymptotic calibration
- A Randomization Rule for Selecting Forecasts
- Universal Portfolios
- Projected Dynamical Systems in the Formulation, Stability Analysis, and Computation of Fixed-Demand Traffic Network Equilibria
- Evolutionary Games and Population Dynamics
- Barrier Operators and Associated Gradient-Like Dynamical Systems for Constrained Minimization Problems
- A Simple Adaptive Procedure Leading to Correlated Equilibrium
- Relatively Smooth Convex Optimization by First-Order Methods, and Applications
- A variational perspective on accelerated methods in optimization
- Prox-Method with Rate of Convergence O(1/t) for Variational Inequalities with Lipschitz Continuous Monotone Operators and Smooth Convex-Concave Saddle Point Problems
- Hessian Riemannian Gradient Flows in Convex Programming
- Singular Riemannian barrier methods and gradient-projection dynamical systems for constrained optimization
- The Nonstochastic Multiarmed Bandit Problem
- Stochastic Approximations and Differential Inclusions
- Adaptive Heuristics
- Prediction, Learning, and Games
- Interior Gradient and Proximal Methods for Convex and Conic Optimization
- Proximité et dualité dans un espace hilbertien
- Existence and Uniqueness of Equilibrium Points for Concave N-Person Games
- On the generalization of a direct method of the calculus of variations
- Weak convergence of the sequence of successive approximations for nonexpansive mappings
- Convex Analysis
- A Descent Lemma Beyond Lipschitz Gradient Continuity: First-Order Methods Revisited and Applications
- Internal regret in on-line portfolio selection
- Potential games with continuous player sets
- A general class of adaptive strategies
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
