English
Related papers

Related papers: Mechanistic Interpretability as Statistical Estima…

200 papers

Explainable AI methods facilitate the understanding of model behaviour, yet, small, imperceptible perturbations to inputs can vastly distort explanations. As these explanations are typically evaluated holistically, before model deployment,…

Machine Learning · Computer Science 2024-06-05 Sara Vera Marjanović , Isabelle Augenstein , Christina Lioma

Mutual information (MI) is an information-theoretic measure of dependency between two random variables. Several methods to estimate MI, from samples of two random variables with unknown underlying probability distributions have been…

Machine Learning · Computer Science 2020-11-18 P Aditya Sreekar , Ujjwal Tiwari , Anoop Namboodiri

Learning meaningful causal representations from observations has emerged as a crucial task for facilitating machine learning applications and driving scientific discoveries in fields such as climate science, biology, and physics. This…

Machine Learning · Computer Science 2026-02-06 Jiaxu Ren , Yixin Wang , Biwei Huang

The rise of the term "mechanistic interpretability" has accompanied increasing interest in understanding neural models -- particularly language models. However, this jargon has also led to a fair amount of confusion. So, what does it mean…

Artificial Intelligence · Computer Science 2024-10-15 Naomi Saphra , Sarah Wiegreffe

Estimating the strength of dependency between two variables is fundamental for exploratory analysis and many other applications in data mining. For example: non-linear dependencies between two continuous variables can be explored with the…

Machine Learning · Statistics 2016-01-21 Simone Romano , Nguyen Xuan Vinh , James Bailey , Karin Verspoor

Computational mechanics, an approach to structural complexity, defines a process's causal states and gives a procedure for finding them. We show that the causal-state representation--an $\epsilon$-machine--is the minimal one consistent with…

Statistical Mechanics · Physics 2022-02-17 Cosma Rohilla Shalizi , James P. Crutchfield

Interpretability is essential in medical imaging to ensure that clinicians can comprehend and trust artificial intelligence models. In this paper, we propose a novel interpretable approach that combines attribute regularization of the…

Image and Video Processing · Electrical Eng. & Systems 2023-12-15 Maxime Di Folco , Cosmin I. Bercea , Julia A. Schnabel

Active learning has long been a topic of study in machine learning. However, as increasingly complex and opaque models have become standard practice, the process of active learning, too, has become more opaque. There has been little…

Machine Learning · Statistics 2018-06-26 Richard L. Phillips , Kyu Hyun Chang , Sorelle A. Friedler

Interpretability and uncertainty quantification in machine learning can provide justification for decisions, promote scientific discovery and lead to a better understanding of model behavior. Symbolic regression provides inherently…

Neural and Evolutionary Computing · Computer Science 2022-11-23 G. F. Bomarito , P. E. Leser , N. C. M Strauss , K. M. Garbrecht , J. D. Hochhalter

Interpretability is central to trustworthy machine learning, yet existing metrics rarely quantify how effectively data support an interpretive representation. We propose Interpretive Efficiency, a normalized, task-aware functional that…

Machine Learning · Computer Science 2025-12-09 Ronald Katende

Predicting the response of nonlinear dynamical systems subject to random, broadband excitation is important across a range of scientific disciplines, such as structural dynamics and neuroscience. Building data-driven models requires…

Machine Learning · Computer Science 2024-09-27 Joseph Massingham , Ole Nielsen , Tore Butlin

Multiple importance sampling (MIS) is an increasingly used methodology where several proposal densities are used to approximate integrals, generally involving target probability density functions. The use of several proposals allows for a…

Statistics Theory · Mathematics 2022-07-12 Rahul Mukerjee , Víctor Elvira

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

Causal discovery is challenging in general dynamical systems because, without strong structural assumptions, the underlying causal graph may not be identifiable even from interventional data. However, many real-world systems exhibit…

Machine Learning · Computer Science 2026-04-07 Panayiotis Panayiotou , Özgür Şimşek

Deep neural networks for medical image classification often fail to generalize consistently in clinical practice due to violations of the i.i.d. assumption and opaque decision-making. This paper examines interpretability in deep neural…

Computer Vision and Pattern Recognition · Computer Science 2025-04-09 Mohammad Hossein Najafi , Mohammad Morsali , Mohammadreza Pashanejad , Saman Soleimani Roudi , Mohammad Norouzi , Saeed Bagheri Shouraki

Explainable AI is an emerging field providing solutions for acquiring insights into automated systems' rationale. It has been put on the AI map by suggesting ways to tackle key ethical and societal issues. Existing explanation techniques…

Machine Learning · Computer Science 2022-05-02 Ioannis Mollas , Nick Bassiliades , Grigorios Tsoumakas

Estimating mutual information (MI) is a fundamental task in data science and machine learning. Existing estimators mainly rely on either highly flexible models (e.g., neural networks), which require large amounts of data, or overly…

Machine Learning · Computer Science 2025-10-27 Yanzhi Chen , Zijing Ou , Adrian Weller , Michael U. Gutmann

In healthcare, predictive models increasingly inform patient-level decisions, yet little attention is paid to the variability in individual risk estimates and its impact on treatment decisions. For overparameterized models, now standard in…

Machine Learning · Computer Science 2026-04-16 Elizabeth W. Miller , Jeffrey D. Blume

Independent component analysis (ICA) is a fundamental statistical tool used to reveal hidden generative processes from observed data. However, traditional ICA approaches struggle with the rotational invariance inherent in Gaussian…

Machine Learning · Computer Science 2024-08-21 Ignavier Ng , Yujia Zheng , Xinshuai Dong , Kun Zhang

Empirical causal claims depend on many analyst decisions, from selecting covariates to choosing estimators. Existing robustness tools summarize how results vary across these choices, but, to the best of our knowledge, do not answer:…

Methodology · Statistics 2026-05-05 Hoang Dang , Luan Pham , Minh Nguyen