English
Related papers

Related papers: Local Interpretable Model-agnostic Explanations of…

200 papers

Providing interpretability of deep-learning models to non-experts, while fundamental for a responsible real-world usage, is challenging. Attribution maps from xAI techniques, such as Integrated Gradients, are a typical example of a…

Computer Vision and Pattern Recognition · Computer Science 2023-11-22 Caroline Mazini Rodrigues , Nicolas Boutry , Laurent Najman

We show that a probabilistic version of the classical forward-stepwise variable inclusion procedure can serve as a general data-augmentation scheme for model space distributions in (generalized) linear models. This latent variable…

Methodology · Statistics 2014-10-23 Li Ma

An increasing number of machine learning models have been deployed in domains with high stakes such as finance and healthcare. Despite their superior performances, many models are black boxes in nature which are hard to explain. There are…

Machine Learning · Statistics 2021-06-16 Zhengze Zhou , Giles Hooker , Fei Wang

The local and global interpretability of various ML models has been studied extensively in recent years. However, despite significant progress in the field, many known results remain informal or lack sufficient mathematical rigor. We…

Machine Learning · Computer Science 2024-06-10 Shahaf Bassan , Guy Amir , Guy Katz

Standard Bayesian inference can build models that combine information from various sources, but this inference may not be reliable if components of a model are misspecified. Cut inference, as a particular type of modularized Bayesian…

Methodology · Statistics 2026-03-18 Yang Liu , Robert J. B. Goudie

A fundamental problem in modern supervised learning is computing reliable conditional prediction intervals in high-dimensional settings: existing methods often rely on restrictive modelling assumptions, do not scale as predictor dimension…

Machine Learning · Statistics 2026-02-24 Daniel Salnikov , Dan Leonte , Kevin Michalewicz

To characterize the Kullback-Leibler divergence and Fisher information in general parametrized hidden Markov models, in this paper, we first show that the log likelihood and its derivatives can be represented as an additive functional of a…

Statistics Theory · Mathematics 2023-03-15 Cheng-Der Fuh , Chu-Lan Michael Kao , Tianxiao Pang

In this study, simultaneous predictive distributions for independent Poisson observables were considered and the performance of predictive distributions was evaluated using the Kullback-Leibler (K-L) loss. This study proposes a class of…

Statistics Theory · Mathematics 2024-02-13 Xiao Li

Large language models (LLMs) have been proposed as alternatives to human experts for estimating unknown quantities with associated uncertainty, a process known as Bayesian elicitation. We test this by asking eleven LLMs to estimate…

Artificial Intelligence · Computer Science 2026-04-03 Luka Hobor , Mario Brcic , Mihael Kovac , Kristijan Poje

While concept-based interpretability methods have traditionally focused on local explanations of neural network predictions, we propose a novel framework and interactive tool that extends these methods into the domain of mechanistic…

Machine Learning · Computer Science 2025-07-09 Sofiia Chorna , Kateryna Tarelkina , Eloïse Berthier , Gianni Franchi

We study the problem of spectrum estimation from transmission data of a known phantom. The goal is to reconstruct an x-ray spectrum that can accurately model the x-ray transmission curves and reflects a realistic shape of the typical energy…

Medical Physics · Physics 2021-07-14 Wooseok Ha , Emil Y. Sidky , Rina Foygel Barber , Taly Gilat Schmidt , Xiaochuan Pan

Generative models and those with computationally intractable likelihoods are widely used to describe complex systems in the natural sciences, social sciences, and engineering. Fitting these models to data requires likelihood-free inference…

Methodology · Statistics 2025-12-04 Rui Zhang , Oksana A. Chkrebtii , Dongbin Xiu

This paper focuses on explaining changes over time in globally-sourced, annual temporal data, with the specific objective of identifying pivotal factors that contribute to these temporal shifts. Leveraging such analytical frameworks can…

Machine Learning · Computer Science 2024-04-19 Shou Nakano , Yang Liu

Multimodal Large Language Models (MLLMs) have shown promise in visual-textual reasoning, with Multimodal Chain-of-Thought (MCoT) prompting significantly enhancing interpretability. However, existing MCoT methods rely on rationale-rich…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Yiwen Jiang , Deval Mehta , Siyuan Yan , Yaling Shen , Zimu Wang , Zongyuan Ge

The Kullback-Leibler (KL) divergence is a fundamental equation of information theory that quantifies the proximity of two probability distributions. Although difficult to understand by examining the equation, an intuition and understanding…

Information Theory · Computer Science 2014-04-09 Jonathon Shlens

The need for interpreting machine learning models is addressed through prototype explanations within the context of tree ensembles. An algorithm named Adaptive Prototype Explanations of Tree Ensembles (A-PETE) is proposed to automatise the…

Machine Learning · Computer Science 2024-06-03 Jacek Karolczak , Jerzy Stefanowski

As machine learning becomes an important part of many real world applications affecting human lives, new requirements, besides high predictive accuracy, become important. One important requirement is transparency, which has been associated…

Machine Learning · Computer Science 2019-08-01 Tiago Botari , Rafael Izbicki , Andre C. P. L. F. de Carvalho

The means by which cortical neural networks are able to efficiently solve inference problems remains an open question in computational neuroscience. Recently, abstract models of Bayesian computation in neural circuits have been proposed,…

Neurons and Cognition · Quantitative Biology 2015-02-24 Dimitri Probst , Mihai A. Petrovici , Ilja Bytschok , Johannes Bill , Dejan Pecevski , Johannes Schemmel , Karlheinz Meier

The self-rationalising capabilities of LLMs are appealing because the generated explanations can give insights into the plausibility of the predictions. However, how faithful the explanations are to the predictions is questionable, raising…

Computation and Language · Computer Science 2024-12-18 Marc Braun , Jenny Kunz

Models often need to be constrained to a certain size for them to be considered interpretable. For example, a decision tree of depth 5 is much easier to understand than one of depth 50. Limiting model size, however, often reduces accuracy.…

Machine Learning · Computer Science 2020-07-02 Abhishek Ghose , Balaraman Ravindran