English
Related papers

Related papers: Trust Regions for Explanations via Black-Box Proba…

200 papers

Local explanation frameworks aim to rationalize particular decisions made by a black-box prediction model. Existing techniques are often restricted to a specific type of predictor or based on input saliency, which may be undesirably…

Machine Learning · Computer Science 2019-02-12 Brandon Carter , Jonas Mueller , Siddhartha Jain , David Gifford

A fundamental challenge in probabilistic modeling is to balance expressivity and inference efficiency. Tractable probabilistic models (TPMs) aim to directly address this tradeoff by imposing constraints that guarantee efficient inference of…

Artificial Intelligence · Computer Science 2025-10-28 John Leland , YooJung Choi

Robust MDPs (RMDPs) can be used to compute policies with provable worst-case guarantees in reinforcement learning. The quality and robustness of an RMDP solution are determined by the ambiguity set---the set of plausible transition…

Machine Learning · Computer Science 2019-02-21 Marek Petrik , Reazul Hasan Russell

Counterfactual explanations for black-box models aim to pr ovide insight into an algorithmic decision to its recipient. For a binary classification problem an individual counterfactual details which features might be changed for the model…

Machine Learning · Statistics 2025-05-29 James M. Adams , Gesine Reinert , Lukasz Szpruch , Carsten Maple , Andrew Elliott

Interpretability methods that utilise local surrogate models (e.g. LIME) are very good at describing the behaviour of the predictive model at a point of interest, but they are not guaranteed to extrapolate to the local region surrounding…

Machine Learning · Computer Science 2024-02-21 Marton Havasi , Sonali Parbhoo , Finale Doshi-Velez

As machine learning systems are increasingly used to make real world legal and financial decisions, it is of paramount importance that we develop algorithms to verify that these systems do not discriminate against minorities. We design a…

Artificial Intelligence · Computer Science 2020-01-01 Osbert Bastani , Xin Zhang , Armando Solar-Lezama

With the increasing complexity of black-box machine learning models and their adoption in high-stakes areas, it is critical to provide explanations for their predictions. Existing local explanation methods lack in generating high-fidelity…

Machine Learning · Computer Science 2026-03-24 Sanjeev Shrestha , Rahul Dubey , Hui Liu

The recent increase in the deployment of machine learning models in critical domains such as healthcare, criminal justice, and finance has highlighted the need for trustworthy methods that can explain these models to stakeholders. Feature…

Machine Learning · Computer Science 2021-10-04 Angeline Yasodhara , Azin Asgarian , Diego Huang , Parinaz Sobhani

With model trustworthiness being crucial for sensitive real-world applications, practitioners are putting more and more focus on improving the uncertainty calibration of deep neural networks. Calibration errors are designed to quantify the…

Machine Learning · Computer Science 2024-03-14 Sebastian G. Gruber , Florian Buettner

The growing use of Machine Learning (ML) tools comes with critical challenges, such as limited model explainability. We propose a global explainability framework that leverages Optimal Transport and Distributionally Robust Optimization to…

Machine Learning · Computer Science 2026-04-23 Adriana Laurindo Monteiro , Jean-Michel Loubes

Large Reasoning Models (LRMs) have recently demonstrated significant improvements in complex reasoning. While quantifying generation uncertainty in LRMs is crucial, traditional methods are often insufficient because they do not provide…

Artificial Intelligence · Computer Science 2026-04-16 Yangyi Li , Chenxu Zhao , Mengdi Huai

Faithful free-text explanations are important to ensure transparency in high-stakes AI decision-making contexts, but they are challenging to generate by language models and assess by humans. In this paper, we present a measure for…

Computation and Language · Computer Science 2025-09-30 Lingjun Zhao , Hal Daumé

Conformal prediction methodologies have significantly advanced the quantification of uncertainties in predictive models. Yet, the construction of confidence regions for model parameters presents a notable challenge, often necessitating…

Machine Learning · Statistics 2024-05-30 Charles Guille-Escuret , Eugene Ndiaye

We introduce a new model-agnostic explanation technique which explains the prediction of any classifier called CLE. CLE gives an faithful and interpretable explanation to the prediction, by approximating the model locally using an…

Machine Learning · Computer Science 2019-10-03 Zijian Zhang , Fan Yang , Haofan Wang , Xia Hu

With the advent of Deep Learning, the field of machine learning (ML) has surpassed human-level performance on diverse classification tasks. At the same time, there is a stark need to characterize and quantify reliability of a model's…

Machine Learning · Computer Science 2021-11-16 Nurali Virani , Naresh Iyer , Zhaoyuan Yang

We consider box-constrained robust optimisation problems with implementation uncertainty. In this setting, the solution that a decision maker wants to implement may become perturbed. The aim is to find a solution that optimises the worst…

Optimization and Control · Mathematics 2018-09-10 Martin Hughes , Marc Goerigk , Michael Wright

Understanding the behavior of learned classifiers is an important task, and various black-box explanations, logical reasoning approaches, and model-specific methods have been proposed. In this paper, we introduce probabilistic sufficient…

Machine Learning · Computer Science 2021-05-24 Eric Wang , Pasha Khosravi , Guy Van den Broeck

ML models are typically trained using large datasets of high quality. However, training datasets often contain inconsistent or incomplete data. To tackle this issue, one solution is to develop algorithms that can check whether a prediction…

Machine Learning · Computer Science 2022-01-19 Austen Z. Fan , Paraschos Koutris

Calibrating blackbox machine learning models to achieve risk control is crucial to ensure reliable decision-making. A rich line of literature has been studying how to calibrate a model so that its predictions satisfy explicit finite-sample…

Machine Learning · Statistics 2025-06-02 Victor Li , Baiting Chen , Yuzhen Mao , Qi Lei , Zhun Deng

*Automated circuit discovery* is a central tool in mechanistic interpretability for identifying the internal components of neural networks responsible for specific behaviors. While prior methods have made significant progress, they…

Machine Learning · Computer Science 2026-02-20 Itamar Hadad , Guy Katz , Shahaf Bassan
‹ Prev 1 3 4 5 6 7 10 Next ›