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.
Interpretable companion model for black-box classifiers.
Black box machine learning models are currently being used for high stakes decision-making throughout society, causing problems throughout healthcare, criminal justice, and in other domains. People have hoped that creating methods for explaining these black box models will alleviate some of these problems, but trying t…
Interpretable machine learning has become a strong competitor for traditional black-box models. However, the possible loss of the predictive performance for gaining interpretability is often inevitable, putting practitioners in a dilemma of choosing between high accuracy (black-box models) and interpretability (interpr…
Driven by an increasing need for model interpretability, interpretable models have become strong competitors for black-box models in many real applications. In this paper, we propose a novel type of model where interpretable models compete and collaborate with black-box models. We present the Model-Agnostic Linear Comp…
This work addresses the situation where a black-box model with good predictive performance is chosen over its interpretable competitors, and we show interpretability is still achievable in this case. Our solution is to find an interpretable substitute on a subset of data where the black-box model is overkill or nearly …
Interpretable deep learning is a fundamental building block towards safer AI, especially when the deployment possibilities of deep learning-based computer-aided medical diagnostic systems are so eminent. However, without a computational formulation of black-box interpretation, general interpretability research rely hea…
The lack of interpretability often makes black-box models difficult to be applied to many practical domains. For this reason, the current work, from the black-box model input port, proposes to incorporate data-based prior information into the black-box soft-margin SVM model to enhance its interpretability. The concept …
Interpretable semi-supervised classifier for black-box models with two self-labeling strategies.
Automated feature engineering improves interpretable models without manual work.
Hybrid models combine interpretable and complex models for better performance and control.
Paper exposes vulnerabilities in interpreting machine learning models using adversarial attacks on PD plots.
We interpret black box predictive models using causal attribution.
IReEn reveals functionality of black-box agents via iterative neural synthesis.
New method improves HPO interpretability without sacrificing performance.
Paper proposes hybrid approach for transparent credit scoring models.
Develops transparent global models consistent with local explanations.
Understanding how a learned black box works is of crucial interest for the future of Machine Learning. In this paper, we pioneer the question of the global interpretability of learned black box models that assign numerical values to symbolic sequential data. To tackle that task, we propose a spectral algorithm for the …
Method makes non-interpretable models more intervenable.
Interpretable machine learning has gained much attention recently. Briefness and comprehensiveness are necessary in order to provide a large amount of information concisely when explaining a black-box decision system. However, existing interpretable machine learning methods fail to consider briefness and comprehensiven…
Most of the work on interpretable machine learning has focused on designing either inherently interpretable models, which typically trade-off accuracy for interpretability, or post-hoc explanation systems, which lack guarantees about their explanation quality. We propose an alternative to these approaches by directly r…
Understanding black-box machine learning models is crucial for their widespread adoption. Learning globally interpretable models is one approach, but achieving high performance with them is challenging. An alternative approach is to explain individual predictions using locally interpretable models. For locally interpre…
Interprets feature interactions in ad-click prediction models.
Paper explores how black box models can deviate from average performance.
DNAMite creates interpretable, calibrated survival analysis models.
SMILE improves explainability of machine learning models.
New method for interpreting complex ML models.
Bayesian optimisation generates saliency maps for black-box models.
Breiman discusses two statistical cultures, advocating for more research on 'before' and 'after' the black box.
This paper uses NLDT to find interpretable control rules from complex DRL policies.
This paper simplifies deep ReLU networks into local linear models for better interpretability.
Matched Machine Learning combines machine learning and matching for causal inference.
Survey interprets foundation models' inner workings.
New method for robustly interpreting ML models using quantile constraints and Wasserstein projections.
System interprets complex treatment effects for personalized policies.
Interpretable surrogates of black-box predictors trained on high-dimensional tabular datasets can struggle to generate comprehensible explanations in the presence of correlated variables. We propose a model-agnostic interpretable surrogate that provides global and local explanations of black-box classifiers to address …
Complex black-box predictive models may have high accuracy, but opacity causes problems like lack of trust, lack of stability, sensitivity to concept drift. On the other hand, interpretable models require more work related to feature engineering, which is very time consuming. Can we train interpretable and accurate mod…
Develops a transparent surrogate model for complex data.
Predictive models are increasingly deployed for the purpose of determining access to services such as credit, insurance, and employment. Despite potential gains in productivity and efficiency, several potential problems have yet to be addressed, particularly the potential for unintentional discrimination. We present an…
Data-trained predictive models see widespread use, but for the most part they are used as black boxes which output a prediction or score. It is therefore hard to acquire a deeper understanding of model behavior, and in particular how different features influence the model prediction. This is important when interpreting…
Multistage Defer Trees improve model accuracy while maintaining interpretability.
Proposes a new method to estimate variable importance in black box models, mitigating correlation effects.
A new method improves the interpretability of data-driven models in ironmaking processes.
A method interprets black-box models using an ensemble of gradient boosting machines.
Black-box explanation is the problem of explaining how a machine learning model -- whose internal logic is hidden to the auditor and generally complex -- produces its outcomes. Current approaches for solving this problem include model explanation, outcome explanation as well as model inspection. While these techniques …
New method wraps black-box classifiers to reduce bias.
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…
As the use of black-box models becomes ubiquitous in high stake decision-making systems, demands for fair and interpretable models are increasing. While it has been shown that interpretable models can be as accurate as black-box models in several critical domains, existing fair classification techniques that are interp…
The paper uses model-based trees to create interpretable surrogate models for complex machine learning models.