NAMLSS models provide interpretable neural regression for location, scale, and shape.
problem Lack of interpretability in deep learning models for complex data distributions.
method Combines classical statistical methods with DNNs for distributional regression.
result Achieves visual interpretability and predictive power of deep learning models.
The paper proposes a consensus algorithm to improve deep neural network interpretability and accuracy in mortality prediction.
problem The black-box nature and overgeneralization of deep neural networks in healthcare applications.
method An (n, k) consensus algorithm that is insensitive to adversarial examples and can reliably reject out-of-distribution samples. result The consensus algorithm improves both prediction accuracy and interpretability of deep neural network models in mortality prediction.
DRN improves actuarial distributional forecasting with interpretable neural networks.
problem Challenges in modeling loss distributional properties with classic methods.
method Combines GLMs with a modified DDR method to flexibly refine baseline distribution.
result DRN improves predictive performance while maintaining interpretability.
L2P predicts heavy-tailed outcomes by placing new instances among known ones.
problem Predicting heavy-tailed outcomes (e.g., best-sellers) with under-prediction by existing methods.
method Learning to Place (L2P) learns pairwise preferences and places new instances to estimate outcomes.
result L2P outperforms existing methods in accuracy and reproducing heavy-tailed distributions.
Locally adaptive interpretable regression improves linear regression's predictability.
problem Linear regression's predictability is limited; it lacks adaptability.
method Locally adaptive interpretable regression (LoAIR) uses neural networks to predict percentile of a Gaussian distribution for regression coefficients.
result LoAIR achieves comparable or better predictive performance than state-of-the-art baselines.
CREDO combines credal and conformal methods to create interpretable prediction intervals.
problem Overconfident prediction intervals in regions of model extrapolation.
method CREDO uses a credal envelope to widen intervals in weak evidence regions and then applies conformal calibration.
result CREDO prediction intervals are interpretable and maintain target coverage.
Proposes SCD-split for CP to balance interpretability and efficiency.
problem Difficult interpretation of disconnected subintervals in CP prediction sets.
method Incorporates smoothing operations into CP framework.
result SCD-split balances interval length and subinterval number, theoretically provable.
New method learns to encode predictions within interpretations, improving evaluation.
problem Need for interpretable machine learning, but existing methods are slow or lack fidelity.
method Amortized explanation methods that learn a global selector model optimizing fidelity of interpretations.
result Predictions can be encoded within interpretations, detected by EVAL-X.
KL-LIME explains Bayesian models by projecting them locally to simpler models.
problem Explaining predictions of complex Bayesian models.
method Combines LIME with Bayesian projection methods.
result Demonstrates improved explanation of MNIST classifications.
New framework models uncertainty in classification debates.
problem Weak interpretability of existing uncertainty quantification methods.
method Courtroom analogy and Mixture of Dirichlet Experts (MoDEX) model.
result MoDEX achieves state-of-the-art uncertainty quantification performance.
New methods predict language model out-of-distribution behaviors using causal mechanisms.
problem Predicting how language models behave on unseen data.
method Two methods: counterfactual simulation and value probing.
result Both methods achieve high AUC-ROC and outperform causal-agnostic approaches in out-of-distribution settings.
The paper proposes a method for interpretable mixture density estimation using a tree structure.
problem Complex probability distributions in machine learning models.
method Interpretable tree structure for mixture density estimation with fast inference.
result The method achieves both high speed and interpretability for mixture density estimation.
Bayesian neural networks reveal multimodal predictive distributions.
problem Uncertainty quantification and interpretability in neural networks.
method Discretized prior for inner layer weights, Gaussian mixture approximation of posterior predictive distribution.
result Distinct parameter realizations can produce the same training error but different posterior predictive distributions.
EAMDrift improves time series prediction accuracy by 20%.
problem Handling unpredictable patterns in time series data.
method Combines forecasts from multiple individual predictors, retraining models automatically.
result EAMDrift outperforms individual baseline models by 20%.
Paper improves predictive distributions for rare events using a simple framework.
problem Local miscalibration of predictive distributions for rare events.
method Semiparametric diagnostic transport maps to correct tail probabilities.
result Semiparametric maps improve predictions for severe weather hazards.
AxNN improves model interpretability without sacrificing predictive power.
problem Black-box nature of machine learning models hinders interpretation and explanation.
method AxNN combines ensembles of generalized additive model networks and additive index models.
result AxNN achieves both good predictive performance and model interpretability.
This paper improves STL inference reliability under covariate shift.
problem Ensuring correct STL formulas in real-world settings with distribution shift.
method Proposes a conformalized STL inference framework that addresses covariate shift.
result Significantly improves symbolic learning reliability at deployment time.
Causal Bayesian networks interpret actions as interventions to connect models to real-world outcomes.
problem Connecting causal model predictions to real-world outcomes.
method Formal framework to interpret actions as interventions and prove impossibility results.
result No non-circular interpretation exists that satisfies natural desiderata without violating some.
COPOD detects outliers efficiently and interpretable using copulas.
problem Outliers in multivariate data are hard to detect efficiently and interpretably.
method COPOD constructs an empirical copula to predict tail probabilities and identify outliers.
result COPOD outperforms existing methods in most cases and is computationally efficient.
We aim to produce predictive models that are not only accurate, but are also interpretable to human experts. Our models are decision lists, which consist of a series of if...then... statements (e.g., if high blood pressure, then stroke) that discretize a high-dimensional, multivariate feature space into a series of sim…
A new method for interpreting AI models using Shapley value for functional data.
problem Interpreting AI models, especially those based on functional data.
method Proposes an interpretability method based on the Shapley value for continuous games.
result Demonstrates the effectiveness of the method through experiments with simulated and real data.
This paper proposes a distributed Bayesian method for piecewise sparse linear models.
problem High computational cost in simultaneous model selection for piecewise linear models.
method Distributed factorized asymptotic Bayesian (FAB) inference on distributed memory architectures.
result Achieves high prediction accuracy and performance scalability.
Bayesian neural network improves ICU patient risk prediction and feature selection.
problem Predicting patient outcomes in ICU with limited interpretability.
method Sparse Bayesian neural network with feature selection.
result Model provides interpretable feature importance for mortality prediction.
Bayesian deep ensembles improve prediction accuracy in various settings.
problem Improving prediction accuracy of deep ensembles in out-of-distribution settings.
method Introducing a randomised, untrainable function to each ensemble member, enabling a posterior predictive distribution interpretation.
result Bayesian deep ensembles make more conservative predictions and outperform standard ensembles in various tasks.
ASTRID method interprets classifier interactions in datasets.
problem Understanding attribute interactions in classification models.
method ASTRID method for investigating attribute interactions.
result ASTRID reveals associations between attributes for better model interpretability.
DFR models dynamic distributional data with weighted Fréchet means.
problem Regression of distribution-valued responses over time.
method Dynamic Fréchet Regression (DFR) with index-aware weighting and feature selection.
result Improved predictive accuracy and feature recovery over existing methods.
New method improves uncertainty calibration in deep learning.
problem Systematic overconfidence in EDL on out-of-distribution inputs.
method Density-Informed Pseudo-count EDL (DIP-EDL) separates class prediction from uncertainty.
result DIP-EDL achieves asymptotic concentration and enhances robustness and uncertainty calibration.
Study uses IMFs and neural networks to predict economic time series, enhancing interpretability.
problem Improving prediction accuracy and interpretability of economic time series.
method Intrinsic Mode Functions (IMFs) derived from economic time series, combined with DeepSHAP for interpretability.
result The last IMFs are most influential, and high-frequency IMFs introduce noise.
Develops a method to discriminate between competing models using Gaussian process surrogates.
problem Discriminating between competing models when data is insufficient and models are non-analytical.
method Introduces Gaussian process surrogates to extend design of experiments methods to non-analytical models.
result Extends design of experiments methods to non-analytical models in a computationally efficient manner.
RAW-Explainer generates interpretable subgraph explanations for link predictions in knowledge graphs.
problem Interpreting GNN predictions for link prediction in heterogeneous settings is challenging.
method RAW-Explainer uses random walk objective and neural network to generate connected, concise subgraph explanations.
result RAW-Explainer strikes a balance between explanation quality and computational efficiency.
Bayesian deep learning uses function-space priors to improve model uncertainty and robustness.
problem Bayesian deep learning struggles with model-specific weight-space priors that are hard to interpret and specify.
method Apply a Dirichlet prior in predictive space and perform approximate function-space variational inference.
result The approach improves uncertainty quantification, scalability, and adversarial robustness in large-scale image classification.
BL learns interpretable optimization structures from data.
problem Learning interpretable optimization structures from data.
method BL parameterizes a compositional utility function from intrinsically interpretable modular blocks.
result BL supports architectures from single to hierarchical compositions, modeling hierarchical optimization structures.
Simplifies RF predictions by focusing on a subset of nearest neighbors.
problem Improving interpretability and performance of RF-based forecast distributions.
method Sparsifying RF-based forecast distributions by focusing on a small subset of nearest neighbors.
result Simplified RF predictions can be similar to or exceed original ones in forecasting performance.
Random Forests provide interpretable prediction intervals with theoretical guarantees.
problem Lack of uncertainty estimates in machine learning point predictions.
method Out-of-Bag procedure for generating parametric and non-parametric prediction intervals.
result Proposed prediction intervals deliver correct coverage rates and narrow lengths.
Optimizes predictions for specific tasks using parametrized decision analysis.
problem Optimizing predictions for specific decision tasks of interest.
method Designs a class of parametrized actions for Bayesian decision analysis.
result Derives efficient and interpretable solutions for various action parametrizations and loss functions.
New measure assesses predictive dependence between continuous variables, capturing non-functional relationships.
problem Quantifying the joint dependence between continuous random variables.
method Introduces a novel, fully non-parametric measure bounded [0,1] that assesses predictive accuracy loss.
result The measure captures a wide range of relationships, including non-functional ones, and is interpretable.
The paper explores how neural networks make predictions using probabilistic programming.
problem Understanding how neural networks make individual predictions.
method Defining and sampling prediction level sets using probabilistic programming.
result The method can obtain examples that result in specified predictions by neural networks.
This study proposes a graph partitioning method to improve spatial prediction models.
problem Improving interpretability of spatial prediction models in industries.
method Graph partitioning problem to minimize within-segment variances, formulated as mixed-integer quadratic programming.
result Approximation scheme efficiently identifies spatial segments, improving computational efficiency.
A new method improves LIME for better model explanation.
problem Current LIME explanations are not faithful and weak in understanding.
method Proposes a novel Modified Perturbed Sampling (MPS) for LIME.
result MPS-LIME achieves better performance in understandability, fidelity, and efficiency.
Paper improves competence estimation of machine learning models.
problem Estimating machine learning performance in real-world scenarios.
method ALICE Score: a pointwise competence estimator considering distributional, data, and model uncertainty.
result Significant improvements in competence prediction over state-of-the-art methods.
Paper proposes a multi-modal probabilistic prediction model for interactive behavior.
problem Predicting future motions of interacting entities in real-world scenarios.
method Generative model for joint prediction of sequential motions of interacting agents.
result Interpretable model capable of handling prediction uncertainties and multi-modal distributions.
Locus scores predictions for risk, reducing large-loss events.
problem Deployment cost from inaccurate predictions, especially large losses.
method Distribution-free loss-scale reliability score using any predictive distribution.
result Reduces large-loss frequency compared to standard heuristics.
New framework converts fairness criteria to social welfare maximization.
problem Interpreting fairness criteria in terms of societal welfare and distribution.
method Converts constrained loss minimization to social welfare maximization problem.
result Predictions and fairness constraints shape societal welfare and distribution.
Conformal prediction offers distribution-free inference for complex models.
problem Traditional predictive inference methods are limited by assumptions about data distributions and model details.
method Conformal prediction uses symmetry assumptions and treats learning algorithms as black boxes.
result Conformal prediction provides exact finite-sample guarantees, even under limited assumptions.
New method interprets complex models for music and urban simulations.
problem Difficulties in understanding deep neural network predictions.
method Uses generative models to improve explanation clarity.
result Flexibility demonstrated across diverse modalities (music, urban simulations).
GNNExplainer provides interpretable explanations for GNN predictions.
problem Explaining GNN predictions remains unsolved due to complex model structure.
method Formulates GNNExplainer as an optimization task maximizing mutual information between prediction and subgraph structures.
result Identifies crucial subgraph structures and node features for GNN predictions.
LaCIM avoids spurious correlation by modeling latent causal factors.
problem Avoiding spurious correlation in supervised learning.
method Introducing latent variables for causal prediction and optimizing over latent space.
result Improved interpretability, robustness, and prediction power on OOD scenarios.
Adapts attention to supervised learning for personalized predictions.
problem Personalized predictions for each data point with model simplicity.
method Local model fitting with attention weighting for tabular data.
result Attention weighting improves predictive performance and preserves interpretability.