Maximum entropy sampling and optimal Bayesian experimental design

By Paola Sebastiani, Henry P. Wynn. 2000

291 citations recorded by the source corpus.

Subfields: Computational Theory and Mathematics, Industrial and Manufacturing Engineering, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/3f1bed633b2d2da333eb87af9e3d1f1cb882fab3

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Industrial and Manufacturing Engineering

In Management Science and Operations Research

Citations in the corpus

Adaptive Gaussian Process Approximation for Bayesian Inference with Expensive Likelihood Functions (2017, methodology): “Here following [21], we choose to quantify the uncertainty in ˆ f ( x ) using the entropy of it, and use it as the design criterion.”
Adaptive Submodularity: Theory and Applications in Active Learning and Stochastic Optimization (2010, methodology): “We would like to adaptively select k sensors, to maximize the expected reduction in Shannon entropy (e.g., Sebastiani and Wynn (2000)).”
Design of computer experiments: A review (2017, methodology): “In case of a Gaussian process model or Kriging, this results in a D-optimal design [144, 173].”
Near-Optimal Sensor Placements in Gaussian Processes: Theory, Efficient Algorithms and Empirical Studies (2008, unknown): “Usually, Bayesian experimental design considers the task of parameter estimation (Sebastiani and Wynn, 2000; Paninski, 2005; Ylvisaker, 1975).”
Bayesian Active Learning for Classification and Preference Learning (2011, methodology): “Information Theoretic approaches: Maximum Entropy Sampling (MES) [Sebastiani and Wynn, 2000] explicitly works in dataspace (Eqn.”
Near-optimal sensor placements in Gaussian processes (2005, unknown): “Usually, Bayesian experimental design considers the task of parameter estimation (Sebastiani and Wynn, 2000; Paninski, 2005; Ylvisaker, 1975).”
Optimal nonlinear Bayesian experimental design: an application to amplitude versus offset experiments (2003, background): “…X may be defined in relation to Shannon’s measure for information (Shannon 1948); see also Tarantola & Valette (1982), Shewry & Wynn (1987) and Sebastiani & Wynn (2000), Ent(X) = −I ( f (x)) + c = − ∫ X f (x) log( f (x)) dx, (5) where f (x) is the p.d.f. of X, and I is the information…”
Simulation-based optimal Bayesian experimental design for nonlinear systems (2011, methodology): “to the maximum entropy sampling approach of Sebastiani and Wynn [11].”
Data-Driven Sparse Sensor Placement for Reconstruction: Demonstrating the Benefits of Exploiting Known Patterns (2017, methodology): “For moderate sized search spaces, the sensor placement problem has well-known model-based solutions using optimal experiment design [1], [2], information theoretic and Bayesian criteria [3], [4], [5], [6], [7] .”
Collaborative Gaussian Processes for Preference Learning (2012, background): “Figure 1 illustrates the differences between BALD and Maximum Entropy Sampling [17] (details in the supplementary material, Section 5).”