Variance regularization in sequential Bayesian optimization

DOI10.1287/MOOR.2019.1019MaRDI QIDQ3387910zbMATH OpenOpenAlexFDO

Authors Michael Jong Kim

Publication date 8 January 2021

Published in Mathematics of Operations Research (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1287/moor.2019.1019

zbMATH Keywords

approximation error boundsBayesian dynamic programmingexploration-exploitation trade-offstrong consistencyvariance regularization

Mathematics Subject Classification ID

Bayesian problems; characterization of Bayes procedures (62C10) Dynamic programming (90C39)

Recommendations

• Bayesian exploration for approximate dynamic programming
• Bayesian optimization
• No-regret Bayesian optimization with unknown hyperparameters
• Dual control for approximate Bayesian reinforcement learning
• Using trajectory data to improve Bayesian optimization for reinforcement learning

Cites work

• A Converse of Taylor's Theorem for Functions on Banach Spaces
• Adaptive Markov control processes
• An Adaptive Bayesian Replacement Policy with Minimal Repair
• An analysis of temporal-difference learning with function approximation
• Bayesian dynamic programming
• Convergence rates of posterior distributions for non iid observations
• Demand estimation and ordering under censoring: stock-out timing is (almost) all you need
• Dynamic selling mechanisms for product differentiation and learning
• scientific article; zbMATH DE number 1818892 (Why is no real title available?)
• scientific article; zbMATH DE number 1478490 (Why is no real title available?)
• scientific article; zbMATH DE number 6846220 (Why is no real title available?)
• scientific article; zbMATH DE number 2107836 (Why is no real title available?)
• scientific article; zbMATH DE number 845714 (Why is no real title available?)
• Joint optimization of sampling and control of partially observable failing systems
• Learning to optimize via posterior sampling
• Least squares policy evaluation algorithms with linear function approximation
• Linear least-squares algorithms for temporal difference learning
• New approaches to Bayesian consistency
• Opaque bank assets and optimal equity capital
• OPTIMAL CONSUMPTION AND PORTFOLIO DECISIONS WITH PARTIALLY OBSERVED REAL PRICES
• Optimal Electoral Timing: Exercise Wisely and You May Live Longer
• Optimal learning and experimentation in bandit problems.
• Rates of convergence of posterior distributions.
• Robust control of partially observable failing systems
• Robust empirical optimization is almost the same as mean-variance optimization
• Robust portfolio techniques for mitigating the fragility of CVaR minimization and generalization to coherent risk measures
• Robust Regression and Lasso
• Robust sensitivity analysis for stochastic systems
• Stochastic optimal control. The discrete time case
• The demand for information: More heat than light
• The knowledge gradient algorithm for a general class of online learning problems
• Thompson Sampling for Stochastic Control: The Continuous Parameter Case
• Thompson Sampling for Stochastic Control: The Finite Parameter Case
• Variance-based regularization with convex objectives

Cited in

(4)

• Optimal control of partially observable semi-Markovian failing systems: an analysis using a phase methodology
• Learning Manipulation Through Information Dissemination
• (Global) optimization: historical notes and recent developments
• Optimal replacement for a partially observable system subject to dependent failure modes

This page was built for publication: Variance regularization in sequential Bayesian optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3387910)