Computing Shapley effects for sensitivity analysis
From MaRDI portal
Abstract: Shapley effects are attracting increasing attention as sensitivity measures. When the value function is the conditional variance, they account for the individual and higher order effects of a model input. They are also well defined under model input dependence. However, one of the issues associated with their use is computational cost. We present a new algorithm that offers major improvements for the computation of Shapley effects, reducing computational burden by several orders of magnitude (from to , where is the number of inputs) with respect to currently available implementations. The algorithm works in the presence of input dependencies. The algorithm also makes it possible to estimate all generalized (Shapley-Owen) effects for interactions.
Recommendations
- Shapley Effects for Global Sensitivity Analysis: Theory and Computation
- Shapley effects for sensitivity analysis with dependent inputs: bootstrap and kriging-based algorithms
- A Shapley-Owen index for interaction quantification
- Variance reduction for estimation of Shapley effects and adaptation to unknown input distribution
- Gaussian linear approximation for the estimation of the Shapley effects
Cites work
- scientific article; zbMATH DE number 5852793 (Why is no real title available?)
- scientific article; zbMATH DE number 5775796 (Why is no real title available?)
- scientific article; zbMATH DE number 49749 (Why is no real title available?)
- scientific article; zbMATH DE number 2060078 (Why is no real title available?)
- scientific article; zbMATH DE number 1529823 (Why is no real title available?)
- scientific article; zbMATH DE number 3078997 (Why is no real title available?)
- A Shapley-Owen index for interaction quantification
- A distribution-free approach to inducing rank correlation among input variables
- A nearest neighbor estimate of the residual variance
- An axiomatic approach to the concept of interaction among players in cooperative games
- An introduction to copulas.
- Analysis of variance designs for model output
- Asymptotic normality and efficiency of two Sobol index estimators
- CAPACITIES AND GAMES ON LATTICES: A SURVEY OF RESULTS
- Combinatorics. A guided tour
- Computational Statistics
- Constructing Sobol Sequences with Better Two-Dimensional Projections
- Equivalent representations of set functions
- Estimating Mean Dimensionality of Analysis of Variance Decompositions
- Estimation of global sensitivity indices for models with dependent variables
- Foundations and methods of stochastic simulation. A first course
- Global sensitivity indices for nonlinear mathematical models and their Monte Carlo estimates
- Making best use of model evaluations to compute sensitivity indices
- Multilinear Extensions of Games
- On Shapley Value for Measuring Importance of Dependent Inputs
- On sensitivity estimation for nonlinear mathematical models
- On the Relative Importance of Input Factors in Mathematical Models
- On the foundations of combinatorial theory I. Theory of M�bius Functions
- Permutations by Interchanges
- Polynomial calculation of the Shapley value based on sampling
- Probabilistic Sensitivity Analysis of Complex Models: A Bayesian Approach
- Reliable error estimation for Sobol' indices
- Remarks on a Multivariate Transformation
- SHAPLEY EFFECTS FOR SENSITIVITY ANALYSIS WITH CORRELATED INPUTS: COMPARISONS WITH SOBOL' INDICES, NUMERICAL ESTIMATION AND APPLICATIONS
- Sensitivity analysis: a review of recent advances
- Sensitivity indices for independent groups of variables
- Set functions, games and capacities in decision making
- Shapley Effects for Global Sensitivity Analysis: Theory and Computation
- Shapley effects for sensitivity analysis with dependent inputs: bootstrap and kriging-based algorithms
- Sobol' indices and Shapley value
- Statistical inference for Sobol pick-freeze Monte Carlo method
- Tensor algorithms for advanced sensitivity metrics
- Transformations and invariance in the sensitivity analysis of computer experiments
- Variance based sensitivity analysis of model output. Design and estimator for the total sensitivity index
- Variance reduction for estimation of Shapley effects and adaptation to unknown input distribution
- Vines -- a new graphical model for dependent random variables.
Cited in
(19)- Estimation of high-order moment-independent importance measures for Shapley value analysis
- Goal-oriented Shapley effects with special attention to the quantile-oriented case
- The many Shapley values for explainable artificial intelligence: a sensitivity analysis perspective
- Sobol' indices and Shapley value
- Proportional marginal effects for global sensitivity analysis
- Variance reduction for estimation of Shapley effects and adaptation to unknown input distribution
- Shapley effects for sensitivity analysis with dependent inputs: bootstrap and kriging-based algorithms
- Block-diagonal covariance estimation and application to the Shapley effects in sensitivity analysis
- Gaussian linear approximation for the estimation of the Shapley effects
- Shapley Effects for Global Sensitivity Analysis: Theory and Computation
- Tail variance allocation, Shapley value, and the majorization problem
- Accelerating the computation of Shapley effects for datasets with many observations
- Shapley effects as a global sensitivity metric for robust design and control
- A Shapley-Owen index for interaction quantification
- Construction of rating systems using global sensitivity analysis: a numerical investigation
- On Shapley Value for Measuring Importance of Dependent Inputs
- Global sensitivity analysis in epidemiological modeling
- An Inference Method for Global Sensitivity Analysis
- Total effects with constrained features
This page was built for publication: Computing Shapley effects for sensitivity analysis
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5158926)
