Proposes CLIQUE for improved local variable importance in multi-class classification.
problem Lack of methods to characterize local structure in model loss space.
method CLIQUE (Conditional Local Importance by Quantile Expectations)
result CLIQUE emphasizes locally dependent information and captures interaction behavior.
New method R-LOCO improves local feature importance analysis.
problem Local attribution methods fail to accurately identify important features.
method R-LOCO segments input space into regions and applies global methods within.
result R-LOCO delivers more accurate local attributions.
New local MDI variable importances derived from global scores match Shapley values.
problem Local feature relevance in tree-based models.
method Deriving local MDI importance measure from global scores and linking it to Shapley values.
result Local MDI importances have a natural connection with Shapley values.
New method identifies important features and interactions in RF models.
problem Limited theoretical understanding of local feature and interaction importance in RF models.
method Combines global and local analysis to identify frequent feature co-occurrences.
result Proves consistent recovery of true local signal features and interactions.
Local MDI+ improves feature importance for tree-based models, enhancing interpretability and performance.
problem Lack of instance-specific feature importance for tree-based models.
method Local MDI+ extends MDI+ framework to provide instance-specific feature importances.
result Local MDI+ outperforms existing baselines, improving predictive performance by 10%.
In recent years, a large amount of model-agnostic methods to improve the transparency, trustability and interpretability of machine learning models have been developed. We introduce local feature importance as a local version of a recent model-agnostic global feature importance method. Based on local feature importance…
Paper proves a Cohen-Dimca-Orlik type theorem for Z-local systems of hyperplane arrangements.
problem Proving a Cohen-Dimca-Orlik type theorem for Z-local systems. method Analyzing local system cohomology groups of hyperplane arrangements complements.
result Proves a Cohen-Dimca-Orlik type theorem for Z-local systems. Adaptive importance sampling for estimating point process statistics.
problem Estimating the expected value of a statistic of a locally stable point process.
method Adaptive importance sampling with Poisson point processes and cross-entropy minimization.
result The proposed estimator converges to the target value almost surely and is asymptotically normal.
Unified view of improving tree model interpretability and debiasing feature importance.
problem Improving interpretability and debiasing feature importance in tree-based models.
method Demonstrates a common thread among bias correction methods and local explanations for trees.
result Points out a bias in explainable AI for trees algorithms due to inbag data inclusion.
LEAPS samples discrete distributions via CTMCs and locally equivariant networks.
problem Sampling from discrete distributions with known normalization.
method Continuous-time Markov chain, locally equivariant functions, attention layers, convolutional networks.
result LEAPS minimizes the variance of importance weights, improving sampling efficiency.
The problem of explaining deep learning models, and model predictions generally, has attracted intensive interest recently. Many successful approaches forgo global approximations in order to provide more faithful local interpretations of the model's behavior. LIME develops multiple interpretable models, each approximat…
Convolutional Neural Networks (CNN) and the locally connected layer are limited in capturing the importance and relations of different local receptive fields, which are often crucial for tasks such as face verification, visual question answering, and word sequence prediction. To tackle the issue, we propose a novel loc…
RbX generates local explanations for black-box models using greedy polytope construction.
problem Generating interpretable local explanations for complex models.
method Greedy algorithm for building a convex polytope to approximate feature regions.
result RbX can more accurately identify important features compared to existing methods.
Evaluates explanations of LTR models using decision paths and compares their accuracy.
problem Challenges in evaluating local explanations of LTR models due to lack of ground truth feature importance scores.
method Focuses on tree-based LTR models, extracts ground truth feature importance scores using decision paths, and compares them with explanation techniques.
result Explanation accuracy varies depending on the model and data point.
Improved interpretability methods for ML models using local regressions and variable importance.
problem Inability of existing interpretability methods to provide reliable explanations for ML models, especially in high-dimensional problems with irrelevant features and non-linear relationships.
method Introduces VarImp and SupClus methods using local regressions with weighted distance considering variable importance.
result VarImp and SupClus methods yield better explanations than state-of-the-art approaches, especially in high-dimensional problems with irrelevant features and non-linear relationships.
Given a loss function F:X→R+ that can be written as the sum of losses over a large set of inputs a1,…,an, it is often desirable to approximate F by subsampling the input points. Strong theoretical guarantees require taking into account the importance of each point, measured by how …
Here we survey on the growth of systoles of arithmetic locally symmetric spaces under the congruence covering and give simple proofs for the best possible constants of Gromov for several important classes of symmetric spaces.
Develops local curvature estimates for mean curvature flow.
problem Sharp curvature pinching estimates for mean curvature flow.
method Local version of Huisken-Stampacchia iteration.
result Local curvature estimates do not depend on noncollapsing quality.
Paper presents a WiFi-based indoor sensor localization technique.
problem Indoor localization in wireless sensor networks.
method Zoning-based localization using statistical learning.
result Efficient sensor zone determination in indoor environments.
Local logarithmic export distributions show non-zero skewness that changes with exporter and destination characteristics.
problem Identifying the skewness in local logarithmic export distributions and its relationship with exporter and destination characteristics.
method Analyzing directed links weighted by the logarithm of export values, studying the skewness of local exports, and formulating quantitative relations.
result Non-zero skewness in local logarithmic export distributions changes with exporter and destination characteristics.
Proposes a method to refine PDE-driven high-dimensional rare-event simulation.
problem Challenges in constructing accurate surrogates for rare-event simulation.
method Adaptive importance sampling framework that refines a locally constructed surrogate.
result Achieves accuracy comparable to true-model adaptive importance sampling with fewer high-fidelity evaluations.
Geodesic completeness proven for all compact locally symmetric Lorentz manifolds.
problem Geodesic completeness of compact locally symmetric Lorentz manifolds.
method Proof in all remaining cases using completeness result.
result All compact, locally symmetric Lorentz manifolds are geodesically complete.
Groups of importance in group theory have flexible stability properties.
problem Stability and flexibility of groups in geometric and combinatorial group theory.
method Establishing Kirchberg's Local Lifting Property and Lubotzky--Shalom's Property FD for specific groups.
result Groups like 3-manifold groups, limit groups, and certain one-relator groups are very flexibly stable. Necessary and sufficient conditions for the exponentiation of finite-dimensional real Lie algebras of linear operators on complete Hausdorff locally convex spaces are obtained, focused on the equicontinuous case - in particular, necessary conditions for exponentiation to compact Lie groups are established. Applications…
Proposes a new method for interpreting feature importance and effects in dependent feature models.
problem Challenges in interpreting feature importance when features are dependent and interactions are present.
method Conditional Subgroup Approach
result Conditional PFI and PDP estimates based on this approach often outperform existing methods.
New methods compare local and global feature importance scores for bioinformatics models.
problem Improving feature importance estimation in tree-based models.
method Comparison of SHAP values and Conditional Feature Contributions (CFCs) for 164 bioinformatics problems.
result SHAP values and CFCs yield similar rankings and interpretations for random forests.
The paper introduces logic constraints to improve AI model interpretability.
problem The black box nature of AI models limits their trustworthiness in high-stakes fields.
method The paper extends AI models with logic constraints to make feature importance more interpretable.
result Promising experimental results have been achieved for the Adult dataset.
The notion of local subgroupoid as a generalisation of a local equivalence relation was defined in a previous paper by the first two authors. Here we use the notion of star path connectivity for a Lie groupoid to give an important new class of examples, generalising the local equivalence relation of a foliation, and de…
We obtain a local Sobolev constant estimate for integral Ricci curvature, which enables us to extend several important tools such as the maximal principle, the gradient estimate, the heat kernel estimate and the L2 Hessian estimate to manifolds with integral Ricci lower bounds, without the non-collapsing conditions.
Extends foliation results to singular cases.
problem Understanding foliations near singular leaves.
method Proves semi-local Levi-Malcev theorem for holonomy Lie algebroid.
result Formal semi-local triviality for all 2-connected and a wide class of 1-connected leaves.
Existing works on "black-box" model interpretation use local-linear approximations to explain the predictions made for each data instance in terms of the importance assigned to the different features for arriving at the prediction. These works provide instancewise explanations and thus give a local view of the model. T…
In this paper, we obtain a localization formula in differential K-theory for S1-action. Then by combining an extension of Goette's result on the comparison of two types of equivariant η-invariants, we establish a version of localization formula for equivariant η-invariants. An important step of our approach is t…
n this paper, we obtain a geometric inequality between the length of the second fundamental form and the length of Lee form in terms of the warping function for a CR-warped product submanifold in a locally conformal Kaehler space form. The equality case is also investigated. Furthermore, the inequality is discussed for…
The automatic detection of critical findings in chest X-rays (CXR), such as pneumothorax, is important for assisting radiologists in their clinical workflow like triaging time-sensitive cases and screening for incidental findings. While deep learning (DL) models has become a promising predictive technology with near-hu…
Investigates maps and properties in spaces with negative dimensions and curvature.
problem Existence of transport maps and local-to-global property in spaces with negative dimensions and bounded Ricci curvature.
method Examines metric measure spaces with negative curvature dimensions and applies reduced curvature-dimension conditions.
result Establishes the existence of transport maps and proves the local-to-global property.
New methods ensure feature importance rankings are correct with high probability.
problem Stability issues in feature importance scores due to random sampling.
method Hypothesis testing-based techniques to assess and verify the stability of top-ranked features.
result Ensures the most important features are correct with high-probability guarantees.
The paper investigates why GNNs struggle to generalize from small to large graphs.
problem Challenges in graph neural networks' ability to generalize across different graph sizes.
method Identified and studied the effect of local structure on size generalization; proposed a novel SSL task.
result GNNs can converge to non-generalizing solutions when there is a discrepancy in local structure.
There are two important statements regarding the Trautman-Bondi mass at null infinity: one is the positivity, and the other is the Bondi mass loss formula, which are both global in nature. In this note, we compute the limit of the Wang-Yau quasi-local mass on unit spheres at null infinity of an asymptotically flat spac…
Framework assesses variable importance for heterogeneous treatment effects.
problem High-risk domains need reliable methods to assess treatment effect heterogeneity.
method Inferential framework based on Shapley values and semiparametric theory.
result Valid inference on variable importance for heterogeneous treatment effects.
TIME explains temporal models by analyzing feature importance.
problem Existing methods struggle with temporal models and feature importance.
method Model-agnostic permutation-based approach, temporal feature importance, hypothesis testing.
result TIME provides statistical rigor for explaining temporal models.
SAGE quantifies feature importance in machine learning models.
problem Understanding the role of individual features in complex models.
method Formalizing predictive power through model-based and universal measures, and introducing SAGE for efficient calculation.
result SAGE assigns more accurate feature importance values than other methods.
We study a secondary invariant, called the Meyer function, on the fundamental group of the complement of the dual variety of a smooth projective variety. This invariant have played an important role when studying the local signatures of fibered 4-manifolds from topological point of view. As an application of our study,…
A robust implementation of a Dupire type local volatility model is an important issue for every option trading floor. Typically, this (inverse) problem is solved in a two step procedure : (i) a smooth parametrization of the implied volatility surface; (ii) computation of the local volatility based on the resulting call…
Local polynomial regression (Fan and Gijbels 1996) is an important class of methods for nonparametric density estimation and regression problems. However, straightforward implementation of local polynomial regression has quadratic time complexity which hinders its applicability in large-scale data analysis. In this pap…
Locally adaptive nearest neighbors improve automated systems' performance and are easier to interpret.
problem Improving automated systems' performance and interpretability.
method Developed a method for k nearest neighbors algorithms to learn locally adaptive metrics.
result Locally adaptive metrics improve performance and are interpretable.
The paper connects machine learning interpretability with learning theory.
problem Performance and explanation generalization in local machine learning models.
method Theoretical analysis and empirical validation of local approximation explanations.
result Theoretical bounds on test-time accuracy and explanation generalization.
New method provides calibrated feature importance explanations for regression models.
problem Lack of uncertainty quantification in existing local explanation methods.
method Extension of Calibrated Explanations method to support regression and probabilistic regression.
result Calibrated Explanations for regression provides quantified uncertainty and robust explanations.
New method compares feature importance and rule extraction for text data interpretability.
problem Unexpected differences in explanations from feature importance and rule extraction methods.
method Proposes a new approach to compare explanations from different methods.
result Different methods can lead to unexpected explanations, even for simple models.