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.
The paper introduces a method to learn models with built-in explanations.
The increasing deployment of machine learning as well as legal regulations such as EU's GDPR cause a need for user-friendly explanations of decisions proposed by machine learning models. Counterfactual explanations are considered as one of the most popular techniques to explain a specific decision of a model. While the…
Machine learning algorithms generally suffer from a problem of explainability. Given a classification result from a model, it is typically hard to determine what caused the decision to be made, and to give an informative explanation. We explore a new method of generating counterfactual explanations, which instead of ex…
A new method for generating counterfactual explanations in high-dimensional datasets.
To construct interpretable explanations that are consistent with the original ML model, counterfactual examples---showing how the model's output changes with small perturbations to the input---have been proposed. This paper extends the work in counterfactual explanations by addressing the challenge of feasibility of su…
δ-CLUE generates diverse explanations for model uncertainty.
This paper proposes new search algorithms for counterfactual explanations based upon mixed integer programming. We are concerned with complex data in which variables may take any value from a contiguous range or an additional set of discrete states. We propose a novel set of constraints that we refer to as a "mixed pol…
Study finds financial constraints explain zero-leverage firms.
Post-hoc explanations of machine learning models are crucial for people to understand and act on algorithmic predictions. An intriguing class of explanations is through counterfactuals, hypothetical examples that show people how to obtain a different prediction. We posit that effective counterfactual explanations shoul…
Method for explaining machine learning survival models using counterfactuals.
In recent years, a number of artificial intelligent services have been developed such as defect detection system or diagnosis system for customer services. Unfortunately, the core in these services is a black-box in which human cannot understand the underlying decision making logic, even though the inspection of the lo…
Proposes a method to generate realistic counterfactuals by learning relationships.
Multi-SpaCE generates valid counterfactual explanations for multivariate time series data.
As data-driven predictive models are increasingly used to inform decisions, it has been argued that decision makers should provide explanations that help individuals understand what would have to change for these decisions to be beneficial ones. However, there has been little discussion on the possibility that individu…
New measure SEV shows non-sparse models can still have low decision sparsity.
Method generates visual explanations for similarity models without classification.
This paper introduces collective counterfactual explanations for groups of instances in classification models.
Unified local and global explanations through functional decomposition of low dimensional structures.
Proposes a constraint for deep clustering to handle both simple and complex topologies.
Proposes a new method to explain model predictions for consumer recourse.
Two oppositely charged droplets of (say) water in e.g. oil or air will tend to drift together under the influence of their charges. As they make contact, one might expect them to coalesce and form one large droplet, and this indeed happens when the charge difference is sufficiently small. However, Ristenpart et al disc…
As machine learning algorithms are increasingly applied to high impact yet high risk tasks, such as medical diagnosis or autonomous driving, it is critical that researchers can explain how such algorithms arrived at their predictions. In recent years, a number of image saliency methods have been developed to summarize …
Predictive models are being increasingly used to support consequential decision making at the individual level in contexts such as pretrial bail and loan approval. As a result, there is increasing social and legal pressure to provide explanations that help the affected individuals not only to understand why a predictio…
New approach to meaningful and robust algorithmic recourse.
A technique scales symbolic methods with gradients for neural model explanation.
A very interesting problem in the classical theory of minimal surfaces consists of the classification of such surfaces under some geometrical and topological constraints. In this short paper, we give a brief summary of the known classification results for properly embedded minimal surfaces with genus zero in $\mathbb{R…
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…
AXE evaluates explanations to avoid misleading Rashomon set model selection.
Machine learning based decision making systems are increasingly affecting humans. An individual can suffer an undesirable outcome under such decision making systems (e.g. denied credit) irrespective of whether the decision is fair or accurate. Individual recourse pertains to the problem of providing an actionable set o…
The paper proposes criteria and methods for evaluating and aggregating feature-based model explanations.
New definition reveals encoding explanations that retain predictive power.
Paper introduces GAMs for interpretable learning-to-rank models.
GRANITE unifies feature-based explanation methods to reduce disagreement.
Differentially private algorithms protect model explanations from leaking training 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…
Zipf's law states that the number of firms with size greater than S is inversely proportional to S. Most explanations start with Gibrat's rule of proportional growth but require additional constraints. We show that Gibrat's rule, at all firm levels, yields Zipf's law under a balance condition between the effective grow…
Improves global counterfactual explanations for model recourse.
New framework evaluates model explanations based on decision task improvement.
G-SHAP generates multiple types of explanations for machine learning models.
Travel decisions tend to exhibit sensitivity to uncertainty and information processing constraints. These behavioural conditions can be characterized by a generative learning process. We propose a data-driven generative model version of rational inattention theory to emulate these behavioural representations. We outlin…
LLMs' explanations are often insufficient and vary with input distribution.
Study finds visual explanations do not significantly improve human accuracy or trust in model predictions.
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…
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…
This research investigates reliable local explanations for machine listening models.
Defines explanations for classifier outcomes using causal concepts.
Our interest in this paper is in the construction of symbolic explanations for predictions made by a deep neural network. We will focus attention on deep relational machines (DRMs, first proposed by H. Lodhi). A DRM is a deep network in which the input layer consists of Boolean-valued functions (features) that are defi…