Managing large-scale transportation infrastructure projects is difficult due to frequent misinformation about the costs which results in large cost overruns that often threaten the overall project viability. This paper investigates the explanations for cost overruns that are given in the literature. Overall, four categ…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,695 papers · 148 categories
Trend · papers per month
48 results for “cost of explanations”
New research challenges the idea that counterfactual explanations should be sparse.
problem Predictive multiplicity leads to multiple models giving almost equal solutions.
method Derive a general upper bound for counterfactual costs under multiplicity and compare sparse vs. data support approaches.
result Data support methods are more robust to multiplicity but have higher counterfactual costs.
Recent work in model-agnostic explanations of black-box machine learning has demonstrated that interpretability of complex models does not have to come at the cost of accuracy or model flexibility. However, it is not clear what kind of explanations, such as linear models, decision trees, and rule lists, are the appropr…
CTE improves explanation estimation with less data and faster computation.
problem Inefficient and inaccurate explanation estimation in machine learning models.
method Distribution compression through kernel thinning to reduce sample size.
result CTE significantly improves accuracy and stability of explanation estimation.
Proposes a method for multilevel explanations of black-box models.
problem Need for explanations at intermediate or group levels, especially for GDPR compliance.
method Meta-method that builds a multilevel explanation tree using local explainability methods.
result Effective multilevel explanations for groups of data points, including novel test points.
DeDUCE efficiently generates realistic counterfactuals for image classifiers.
problem Generating accurate counterfactual explanations for large image classifiers.
method Developed a new algorithm using spectral normalization to efficiently generate counterfactuals.
result Our algorithm consistently produces counterfactuals closer to the original inputs with comparable realism.
Proposes an efficient method for ordered counterfactual explanations.
problem Insufficient explanation of perturbation vectors for executing actions.
method Mixed-Integer Linear Optimization (MILP) approach for evaluating and extracting optimal pairs of actions and orders.
result Demonstrated effectiveness of the proposed method on real datasets.
Proposes approximating computationally expensive explainability techniques using conformal regression.
problem Computational expense of score-based explainability techniques limits their applicability in time-critical contexts.
method Uses conformal prediction framework to approximate SHAP and TreeSHAP explanations.
result Significantly improves execution time and produces tight validity guarantees.
A fast method for finding counterfactual explanations for decision forests.
problem Finding counterfactual explanations for decision forests efficiently.
method Constrain optimization to data-populated regions, reducing to nearest-neighbor search.
result Very fast and realistic counterfactual explanations for decision forests.
SAGE-FIN detects financial fraud using GNNs and Granger causality.
problem Detecting fraud in financial networks with limited labeled data and lack of explainability.
method Semi-supervised GNN approach with Granger causal explanations.
result SAGE-FIN outperforms on real-world financial network dataset with explainable flagged items.
A method uses Shapley values and Mahalanobis distances to explain multivariate outliers.
problem Explaining multivariate outlyingness in data.
method Decomposing squared Mahalanobis distance using Shapley values.
result Shapley values provide variable contributions to outlying observations.
Paper explains why small-loss criterion works for learning from noisy labels.
problem Learning from noisy labels in deep learning with limited labeled data.
method Theoretical analysis and reformulation of the small-loss criterion.
result Theoretical explanation and reformulation of the small-loss criterion.
Mode connectivity is a surprising phenomenon in the loss landscape of deep nets. Optima -- at least those discovered by gradient-based optimization -- turn out to be connected by simple paths on which the loss function is almost constant. Often, these paths can be chosen to be piece-wise linear, with as few as two segm…
FastSHAP speeds up Shapley value estimation for black-box models.
problem Efficiently calculating Shapley values for complex models.
method Uses a learned explainer model in a single forward pass.
result Generates high-quality explanations with significant speedup.
This paper introduces collective counterfactual explanations for groups of instances in classification models.
problem Understanding how classification models make decisions for groups of instances.
method Novel Mathematical Optimization models to find collective counterfactual explanations that minimize total perturbation cost.
result Detects critical features for entire dataset classification and handles outliers.
Strategic behaviour is one of the main explanations for cost overruns. It can theoretically be supported by agency theory, in which strategic behaviour is the result of asymmetric information between the principal and agent. This paper gives a formal account of this relation by a signalling game. This is a game with in…
Automates investor/company matching with AI, explaining decisions.
problem Matching companies and investors is hard due to limited data and need for explanations.
method Representation learning for small datasets + parameterized explanation generation.
result System performs well on matching task and explains decisions.
With the rise of deep neural networks for quantum chemistry applications, there is a pressing need for architectures that, beyond delivering accurate predictions of chemical properties, are readily interpretable by researchers. Here, we describe interpretation techniques for atomistic neural networks on the example of …
Two new algorithms speed up TreeSHAP computation for tree-based models.
problem Slow computation of SHAP values on tree-based models.
method Two new algorithms, Fast TreeSHAP v1 and v2, designed to improve computational efficiency.
result Fast TreeSHAP v2 is 2.5x faster than TreeSHAP, with slightly higher memory usage.
Proposes a method to generate counterfactuals for ensemble models using entropic risk measures.
problem Finding a single counterfactual explanation for an ensemble of models.
method Incorporates entropic risk measure into a constrained optimization to generate counterfactuals valid for an adjustable fraction of models.
result Entropic risk measure allows generation of counterfactuals valid for all models in the ensemble under a limiting case.
New method converts LVAs into linear projections for better understanding of complex models.
problem Limited interpretability of nonlinear machine learning models.
method Animated linear projections and radial tours.
result Improved understanding of variable importance in complex models.
Model cash management under ambiguity using maxmin preferences and diffusion.
problem Optimizing cash reserves in the presence of ambiguity.
method Singular control model with maxmin preferences, verified using Dynkin games.
result Higher expected costs and narrower inaction region under increased ambiguity.
Because of the prominent position of urban rail in reducing urban transport-related problems, such as congestion and air pollution, insights into the costs of possible new urban rail projects is very relevant for those involved with cost estimations, policy makers, cost-benefit analysts, and other target groups. Knowle…
Many methods to explain black-box models, whether local or global, are additive. In this paper, we study global additive explanations for non-additive models, focusing on four explanation methods: partial dependence, Shapley explanations adapted to a global setting, distilled additive explanations, and gradient-based e…
Small LLMs outperform large ones on simple tasks without extra labelling costs.
problem Performance of large commercial models in simple classification tasks.
method Logistic Regression on small LLM embeddings.
result Small LLMs equal or outperform large LLMs in 'tens-of-shot' classification tasks.
Develops Shapley explainability solutions respecting data manifold.
problem Tenable assumption of uncorrelated features in Shapley explainability.
method Two solutions: generative modelling and direct learning of Shapley value-function.
result On-manifold Shapley explainability overcomes drawbacks of 'off-manifold' values.
Deep Neural Networks (DNNs) deliver state-of-the-art performance in many image recognition and understanding applications. However, despite their outstanding performance, these models are black-boxes and it is hard to understand how they make their decisions. Over the past few years, researchers have studied the proble…
AXE evaluates explanations to avoid misleading Rashomon set model selection.
problem Evaluating explanations for Rashomon set models to avoid false selection.
method Proposed AXE method to evaluate explanation quality.
result AXE detects adversarial fairwashing with 100% success rate.
The paper proposes criteria and methods for evaluating and aggregating feature-based model explanations.
problem Lack of quantitative evaluation criteria for feature-based model explanations.
method Developed quantitative evaluation criteria (low sensitivity, high faithfulness, low complexity), devised a framework for aggregation, and derived a new aggregate Shapley value explanation function.
result A new aggregate Shapley value explanation function that minimizes sensitivity.
New definition reveals encoding explanations that retain predictive power.
problem Challenges in evaluating and identifying encoding explanations.
method Developed a definition of encoding based on conditional dependence.
result Existing evaluation scores do not rank non-encoding explanations correctly, but STRIPE-X does.
Adversarial training leads to large generalization gap, decomposed into bias and variance.
problem Understanding the large generalization gap in adversarially trained models.
method Bias-Variance decomposition of test risk as a function of adversarial perturbation radius.
result Bias increases monotonically with adversarial perturbation radius and is dominant in test risk.
GRANITE: A Generalized Regional Framework for Identifying Agreement in Feature-Based Explanationsstat.ML
GRANITE unifies feature-based explanation methods to reduce disagreement.
problem Disagreement among feature-based explanation methods.
method GRANITE partitions feature space into regions minimizing interaction and distribution influences.
result Unified and consistent feature explanations.
Optimal DP mechanisms for vector queries are found to be staircase distributions.
problem Designing optimal additive mechanisms for vector-valued queries under differential privacy.
method Reduction to radially symmetric distributions and convex rearrangement theory.
result Staircase mechanisms are optimal for any norm and cost function.
Differentially private algorithms protect model explanations from leaking training data.
problem Model explanations can leak training data, compromising privacy.
method Adaptive differentially private gradient descent algorithm to produce accurate, private explanations.
result Privacy amplification and reduction of overall privacy loss on explanation data.
We consider objective evaluation measures of saliency explanations for complex black-box machine learning models. We propose simple robust variants of two notions that have been considered in recent literature: (in)fidelity, and sensitivity. We analyze optimal explanations with respect to both these measures, and while…
In fixed income sector, the yield curve is probably the most observed indicator by the market for trading and fifinancing purposes. A yield curve plots interest rates across different contract maturities from short end to as long as 30 years. For each currency, the corresponding curve shows the relation between the lev…
Improves global counterfactual explanations for model recourse.
problem Inability to provide explanations beyond local instances.
method Investigates and improves Actionable Recourse Summaries (AReS) for global counterfactual explanations.
result Develops more efficient and interactive explainability tools.
New framework evaluates model explanations based on decision task improvement.
problem Evaluation of model explanations often misses practical value.
method Decision-theoretic framework quantifying three key values.
result Provides benchmarks and interprets human-AI decision support.
We define and compute plausible counterfactual explanations using density constraints.
problem Efficiently compute plausible counterfactual explanations for machine learning models.
method Propose and study a formal definition of plausible counterfactual explanations, use density estimators, and introduce convex density constraints.
result Convex density constraints ensure plausible and feasible counterfactual explanations.
Lock-in, the escalating commitment of decision-makers to an ineffective course of action, has the potential to explain the large cost overruns in large scale transportation infrastructure projects. Lock-in can occur both at the decision-making level (before the decision to build) and at the project level (after the dec…
In reinforcement learning, the TD() algorithm is a fundamental policy evaluation method with an efficient online implementation that is suitable for large-scale problems. One practical drawback of TD() is its sensitivity to the choice of the step-size. It is an empirically well-known fact that a large step-size l…
G-SHAP generates multiple types of explanations for machine learning models.
problem Understanding model predictions and their differences across groups.
method Generalization of SHAP method to produce additional types of explanations.
result G-SHAP produces explanations for classification, intergroup differences, and model failure.
LLMs' explanations are often insufficient and vary with input distribution.
problem Evaluating the sufficiency of LLM explanations without predefined biases.
method Generalizing sufficiency to arbitrary explanations, using LLM's input beliefs, and introducing SCSuff metric.
result Explanation sufficiency can vary with input distribution and is weakly correlated with model size, accuracy, or output entropy.
Study finds visual explanations do not significantly improve human accuracy or trust in model predictions.
problem Measuring the impact of visual explanations on human accuracy and trust in model predictions.
method Randomized controlled trial with image-based age prediction task, varying levels of explanation quality.
result Visual explanations do not significantly alter human accuracy or trust in the model.
Despite a growing literature on explaining neural networks, no consensus has been reached on how to explain a neural network decision or how to evaluate an explanation. Our contributions in this paper are twofold. First, we investigate schemes to combine explanation methods and reduce model uncertainty to obtain a sing…
Many proposed methods for explaining machine learning predictions are in fact challenging to understand for nontechnical consumers. This paper builds upon an alternative consumer-driven approach called TED that asks for explanations to be provided in training data, along with target labels. Using semi-synthetic data fr…
This research investigates reliable local explanations for machine listening models.
problem Generating reliable local explanations for machine listening models.
method Investigates the sensitivity of SoundLIME explanations to input perturbations and proposes a novel method for identifying suitable content types.
result SoundLIME explanations are sensitive to the content in occluded input regions, and the average magnitude of input mel-spectrogram bins is the most suitable content type for temporal explanations.
Defines explanations for classifier outcomes using causal concepts.
problem Understanding classifier outcomes in a causal context.
method Proposes a new definition of explanation based on causality, compares it with existing notions, and evaluates it experimentally.
result Experimental evaluation shows the new definition's effectiveness on financial datasets.