Statistically Valid Variable Importance Assessment through Conditional Permutations

• URL: http://arxiv.org/abs/2309.07593v2
• Date: Wed, 25 Oct 2023 23:34:58 GMT
• Title: Statistically Valid Variable Importance Assessment through Conditional Permutations
• Authors: Ahmad Chamma (1 and 2 and 3), Denis A. Engemann (4) and Bertrand Thirion (1 and 2 and 3) ((1) Inria, (2) Universite Paris Saclay, (3) CEA, (4) Roche Pharma Research and Early Development, Neuroscience and Rare Diseases, Roche Innovation Center Basel, F. Hoffmann-La Roche Ltd., Basel, Switzerland)
• Abstract summary: Conditional Permutation Importance is a new approach to variable importance assessment. We show that $textitCPI$ overcomes the limitations of standard permutation importance by providing accurate type-I error control. Our results suggest that $textitCPI$ can be readily used as drop-in replacement for permutation-based methods.
• Score: 19.095605415846187
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Variable importance assessment has become a crucial step in machine-learning applications when using complex learners, such as deep neural networks, on large-scale data. Removal-based importance assessment is currently the reference approach, particularly when statistical guarantees are sought to justify variable inclusion. It is often implemented with variable permutation schemes. On the flip side, these approaches risk misidentifying unimportant variables as important in the presence of correlations among covariates. Here we develop a systematic approach for studying Conditional Permutation Importance (CPI) that is model agnostic and computationally lean, as well as reusable benchmarks of state-of-the-art variable importance estimators. We show theoretically and empirically that $\textit{CPI}$ overcomes the limitations of standard permutation importance by providing accurate type-I error control. When used with a deep neural network, $\textit{CPI}$ consistently showed top accuracy across benchmarks. An experiment on real-world data analysis in a large-scale medical dataset showed that $\textit{CPI}$ provides a more parsimonious selection of statistically significant variables. Our results suggest that $\textit{CPI}$ can be readily used as drop-in replacement for permutation-based methods.

Related papers

• Semiparametric conformal prediction [79.6147286161434]
  Risk-sensitive applications require well-calibrated prediction sets over multiple, potentially correlated target variables. We treat the scores as random vectors and aim to construct the prediction set accounting for their joint correlation structure. We report desired coverage and competitive efficiency on a range of real-world regression problems.
  arXiv  Detail & Related papers  (2024-11-04T14:29:02Z)
• Improving importance estimation in covariate shift for providing accurate prediction error [0.0]
  The Kullback-Leibler Importance Estimation Procedure (KLIEP) is capable of estimating importance in a promising way. This paper explores the potential performance improvement if target information is considered in the computation of the importance.
  arXiv  Detail & Related papers  (2024-02-02T14:39:39Z)
• Variable Importance in High-Dimensional Settings Requires Grouping [19.095605415846187]
  Conditional Permutation Importance (CPI) bypasses PI's limitations in such cases. Grouping variables statistically via clustering or some prior knowledge gains some power back. We show that the approach extended with stacking controls the type-I error even with highly-correlated groups.
  arXiv  Detail & Related papers  (2023-12-18T00:21:47Z)
• DiscoVars: A New Data Analysis Perspective -- Application in Variable Selection for Clustering [0.0]
  We present a new data analysis perspective to determine variable importance regardless of the underlying learning task. We propose a new methodology to select important variables from the data by first creating dependency networks among all variables. We present our tool as a Shiny app which is a user-friendly interface development environment.
  arXiv  Detail & Related papers  (2023-04-08T10:57:19Z)
• Determination of class-specific variables in nonparametric multiple-class classification [0.0]
  We propose a probability-based nonparametric multiple-class classification method, and integrate it with the ability of identifying high impact variables for individual class. We report the properties of the proposed method, and use both synthesized and real data sets to illustrate its properties under different classification situations.
  arXiv  Detail & Related papers  (2022-05-07T10:08:58Z)
• Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning [78.83598532168256]
  Marginal-likelihood based model-selection is rarely used in deep learning due to estimation difficulties. Our work shows that marginal likelihoods can improve generalization and be useful when validation data is unavailable.
  arXiv  Detail & Related papers  (2021-04-11T09:50:24Z)
• SLOE: A Faster Method for Statistical Inference in High-Dimensional Logistic Regression [68.66245730450915]
  We develop an improved method for debiasing predictions and estimating frequentist uncertainty for practical datasets. Our main contribution is SLOE, an estimator of the signal strength with convergence guarantees that reduces the computation time of estimation and inference by orders of magnitude.
  arXiv  Detail & Related papers  (2021-03-23T17:48:56Z)
• Brain Image Synthesis with Unsupervised Multivariate Canonical CSC$\ell_4$Net [122.8907826672382]
  We propose to learn dedicated features that cross both intre- and intra-modal variations using a novel CSC$ell_4$Net.
  arXiv  Detail & Related papers  (2021-03-22T05:19:40Z)
• Nonlinear Distribution Regression for Remote Sensing Applications [6.664736150040092]
  In many remote sensing applications one wants to estimate variables or parameters of interest from observations. Standard algorithms such as neural networks, random forests or Gaussian processes are readily available to relate to the two. This paper introduces a nonlinear (kernel-based) method for distribution regression that solves the previous problems without making any assumption on the statistics of the grouped data.
  arXiv  Detail & Related papers  (2020-12-07T22:04:43Z)
• Unlabelled Data Improves Bayesian Uncertainty Calibration under Covariate Shift [100.52588638477862]
  We develop an approximate Bayesian inference scheme based on posterior regularisation. We demonstrate the utility of our method in the context of transferring prognostic models of prostate cancer across globally diverse populations.
  arXiv  Detail & Related papers  (2020-06-26T13:50:19Z)
• Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift [81.74795324629712]
  We call prediction-time batch normalization, which significantly improves model accuracy and calibration under covariate shift. We show that prediction-time batch normalization provides complementary benefits to existing state-of-the-art approaches for improving robustness. The method has mixed results when used alongside pre-training, and does not seem to perform as well under more natural types of dataset shift.
  arXiv  Detail & Related papers  (2020-06-19T05:08:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.