Related papers: S-CFE: Simple Counterfactual Explanations

S-CFE: Simple Counterfactual Explanations

URL: http://arxiv.org/abs/2410.15723v1
Date: Mon, 21 Oct 2024 07:42:43 GMT
Title: S-CFE: Simple Counterfactual Explanations
Authors: Shpresim Sadiku, Moritz Wagner, Sai Ganesh Nagarajan, Sebastian Pokutta,
Abstract summary: We tackle the problem of finding manifold-aligned counterfactual explanations for sparse data. Our approach effectively produces sparse, manifold-aligned counterfactual explanations.
Score: 21.975560789792073
License:
Abstract: We study the problem of finding optimal sparse, manifold-aligned counterfactual explanations for classifiers. Canonically, this can be formulated as an optimization problem with multiple non-convex components, including classifier loss functions and manifold alignment (or \emph{plausibility}) metrics. The added complexity of enforcing \emph{sparsity}, or shorter explanations, complicates the problem further. Existing methods often focus on specific models and plausibility measures, relying on convex $\ell_1$ regularizers to enforce sparsity. In this paper, we tackle the canonical formulation using the accelerated proximal gradient (APG) method, a simple yet efficient first-order procedure capable of handling smooth non-convex objectives and non-smooth $\ell_p$ (where $0 \leq p < 1$) regularizers. This enables our approach to seamlessly incorporate various classifiers and plausibility measures while producing sparser solutions. Our algorithm only requires differentiable data-manifold regularizers and supports box constraints for bounded feature ranges, ensuring the generated counterfactuals remain \emph{actionable}. Finally, experiments on real-world datasets demonstrate that our approach effectively produces sparse, manifold-aligned counterfactual explanations while maintaining proximity to the factual data and computational efficiency.

Related papers

Stochastic Inexact Augmented Lagrangian Method for Nonconvex Expectation Constrained Optimization [88.0031283949404]
Many real-world problems have complicated non functional constraints and use a large number of data points. Our proposed method outperforms an existing method with the previously best-known result.
arXiv Detail & Related papers (2022-12-19T14:48:54Z)
Multi-block-Single-probe Variance Reduced Estimator for Coupled Compositional Optimization [49.58290066287418]
We propose a novel method named Multi-block-probe Variance Reduced (MSVR) to alleviate the complexity of compositional problems. Our results improve upon prior ones in several aspects, including the order of sample complexities and dependence on strongity.
arXiv Detail & Related papers (2022-07-18T12:03:26Z)
Efficient and Flexible Sublabel-Accurate Energy Minimization [62.50191141358778]
We address the problem of minimizing a class of energy functions consisting of data and smoothness terms. Existing continuous optimization methods can find sublabel-accurate solutions, but they are not efficient for large label spaces. We propose an efficient sublabel-accurate method that utilizes the best properties of both continuous and discrete models.
arXiv Detail & Related papers (2022-06-20T06:58:55Z)
Sharper Rates and Flexible Framework for Nonconvex SGD with Client and Data Sampling [64.31011847952006]
We revisit the problem of finding an approximately stationary point of the average of $n$ smooth and possibly non-color functions. We generalize the $smallsfcolorgreen$ so that it can provably work with virtually any sampling mechanism. We provide the most general and most accurate analysis of optimal bound in the smooth non-color regime.
arXiv Detail & Related papers (2022-06-05T21:32:33Z)
Faster One-Sample Stochastic Conditional Gradient Method for Composite Convex Minimization [61.26619639722804]
We propose a conditional gradient method (CGM) for minimizing convex finite-sum objectives formed as a sum of smooth and non-smooth terms. The proposed method, equipped with an average gradient (SAG) estimator, requires only one sample per iteration. Nevertheless, it guarantees fast convergence rates on par with more sophisticated variance reduction techniques.
arXiv Detail & Related papers (2022-02-26T19:10:48Z)
Sparse Quadratic Optimisation over the Stiefel Manifold with Application to Permutation Synchronisation [71.27989298860481]
We address the non- optimisation problem of finding a matrix on the Stiefel manifold that maximises a quadratic objective function. We propose a simple yet effective sparsity-promoting algorithm for finding the dominant eigenspace matrix.
arXiv Detail & Related papers (2021-09-30T19:17:35Z)
Causality-based Counterfactual Explanation for Classification Models [11.108866104714627]
We propose a prototype-based counterfactual explanation framework (ProCE) ProCE is capable of preserving the causal relationship underlying the features of the counterfactual data. In addition, we design a novel gradient-free optimization based on the multi-objective genetic algorithm that generates the counterfactual explanations.
arXiv Detail & Related papers (2021-05-03T09:25:59Z)
Quasi-Newton Solver for Robust Non-Rigid Registration [35.66014845211251]
We propose a formulation for robust non-rigid registration based on a globally smooth robust estimator for data fitting and regularization. We apply the majorization-minimization algorithm to the problem, which reduces each iteration to solving a simple least-squares problem with L-BFGS.
arXiv Detail & Related papers (2020-04-09T01:45:05Z)
Entropy Regularized Power k-Means Clustering [21.013169939337583]
We propose a scalable majorization-minimization algorithm that enjoys closed-form updates and convergence guarantees. Our method retains the same computational complexity of $k$-means and power $k$-means, but yields significant improvements over both.
arXiv Detail & Related papers (2020-01-10T14:05:44Z)

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