Sequential design for ranking response surfaces
From MaRDI portal
Publication:5269860
DOI10.1137/15M1045168zbMATH Open1365.62319arXiv1509.00980MaRDI QIDQ5269860FDOQ5269860
Publication date: 28 June 2017
Published in: SIAM/ASA Journal on Uncertainty Quantification (Search for Journal in Brave)
Abstract: We propose and analyze sequential design methods for the problem of ranking several response surfaces. Namely, given response surfaces over a continuous input space , the aim is to efficiently find the index of the minimal response across the entire . The response surfaces are not known and have to be noisily sampled one-at-a-time. This setting is motivated by stochastic control applications and requires joint experimental design both in space and response-index dimensions. To generate sequential design heuristics we investigate stepwise uncertainty reduction approaches, as well as sampling based on posterior classification complexity. We also make connections between our continuous-input formulation and the discrete framework of pure regret in multi-armed bandits. To model the response surfaces we utilize kriging surrogates. Several numerical examples using both synthetic data and an epidemics control problem are provided to illustrate our approach and the efficacy of respective adaptive designs.
Full work available at URL: https://arxiv.org/abs/1509.00980
Recommendations
sequential designstochastic krigingexpected improvementresponse surface modelingsequential uncertainty reduction
Gaussian processes (60G15) Statistical ranking and selection procedures (62F07) Sequential statistical design (62L05) Response surface designs (62K20)
Cites Work
- Efficient global optimization of expensive black-box functions
- BART: Bayesian additive regression trees
- Stochastic Kriging for Simulation Metamodeling
- Title not available (Why is that?)
- Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting
- Title not available (Why is that?)
- On posterior consistency in nonparametric regression problems
- A Comparison of Three Methods for Selecting Values of Input Variables in the Analysis of Output from a Computer Code
- A Nonstationary Space-Time Gaussian Process Model for Partially Converged Simulations
- Sequential design of computer experiments for the estimation of a probability of failure
- Sequential Design for Optimal Stopping Problems
- Finite-time analysis of the multiarmed bandit problem
- Sequential Bayesian inference in hidden Markov stochastic kinetic models with application to detection and response to seasonal epidemics
- A Probabilistic Numerical Method for Optimal Multiple Switching Problems in High Dimension
- Monte Carlo algorithms for optimal stopping and statistical learning
- Dynamic Trees for Learning and Design
- Valuation of Storage at a Liquefied Natural Gas Terminal
- MONTE CARLO METHODS FOR THE VALUATION OF MULTIPLE‐EXERCISE OPTIONS
- Buy-low and sell-high investment strategies
- Smart Sleeping Policies for Energy Efficient Tracking in Sensor Networks
- Pure exploration in finitely-armed and continuous-armed bandits
- Upper-Confidence-Bound Algorithms for Active Learning in Multi-armed Bandits
Cited In (14)
- Efficient sequential experimental design for surrogate modeling of nested codes
- Discrete-type approximations for non-Markovian optimal stopping problems. II
- Deep learning for ranking response surfaces with applications to optimal stopping problems
- Continuous multi-task Bayesian optimisation with correlation
- Moment independent uncertainty importance measure for stochastic systems based on Gaussian process
- Title not available (Why is that?)
- Technical note—Knowledge gradient for selection with covariates: Consistency and computation
- Recent developments in machine learning methods for stochastic control and games
- Large-scale local surrogate modeling of stochastic simulation experiments
- Ranking and Selection with Covariates for Personalized Decision Making
- Sparse Polynomial Chaos Expansions: Literature Survey and Benchmark
- Evaluating Gaussian process metamodels and sequential designs for noisy level set estimation
- Practical Heteroscedastic Gaussian Process Modeling for Large Simulation Experiments
- Phenomenological forecasting of disease incidence using heteroskedastic Gaussian processes: a dengue case study
Uses Software
This page was built for publication: Sequential design for ranking response surfaces
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5269860)
