A continuous-time approach to online optimization
From MaRDI portal
Publication:520967
DOI10.3934/jdg.2017008zbMath1359.90095arXiv1401.6956OpenAlexW2964294891WikidataQ60142047 ScholiaQ60142047MaRDI QIDQ520967
Publication date: 6 April 2017
Published in: Journal of Dynamics and Games (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1401.6956
convex optimizationcontinuous timegradient descentonline optimizationregret minimizationmirror descent
Related Items (11)
Replicator dynamics: old and new ⋮ Stochastic mirror descent dynamics and their convergence in monotone variational inequalities ⋮ Exploration-exploitation in multi-agent learning: catastrophe theory meets game theory ⋮ No-regret algorithms in on-line learning, games and convex optimization ⋮ Continuous time learning algorithms in optimization and game theory ⋮ On the Convergence of Gradient-Like Flows with Noisy Gradient Input ⋮ A survey of gradient methods for solving nonlinear optimization ⋮ Learning in Games via Reinforcement and Regularization ⋮ Scale-Free Algorithms for Online Linear Optimization ⋮ From Darwin to Poincaré and von Neumann: recurrence and cycles in evolutionary and algorithmic game theory ⋮ Learning in nonatomic games. I: Finite action spaces and population games
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Primal-dual subgradient methods for convex problems
- Consistency and cautious fictitious play
- Exponentiated gradient versus gradient descent for linear predictors
- Exponential weight algorithm in continuous time
- A game of prediction with expert advice
- The weighted majority algorithm
- Adaptive and self-confident on-line learning algorithms
- Mirror descent and nonlinear projected subgradient methods for convex optimization.
- Conditional universal consistency.
- Analysis of two gradient-based algorithms for on-line regression
- Online Learning and Online Convex Optimization
- Robust Stochastic Approximation Approach to Stochastic Programming
- Variational Analysis
- How to use expert advice
- Consistency of Vanishingly Smooth Fictitious Play
- Stochastic Approximations and Differential Inclusions, Part II: Applications
- Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems
- Prediction by Categorical Features: Generalization Properties and Application to Feature Ranking
- Prediction, Learning, and Games
- On the Global Convergence of Stochastic Fictitious Play
- Convex Analysis
This page was built for publication: A continuous-time approach to online optimization