English
Related papers

Related papers: Understanding Black-box Predictions via Influence …

200 papers

Labeling bias arises during data collection due to resource limitations or unconscious bias, leading to unequal label error rates across subgroups or misrepresentation of subgroup prevalence. Most fairness constraints assume training labels…

Machine Learning · Computer Science 2026-02-24 Frida Jørgensen , Nina Weng , Siavash Bigdeli

Machine-learned models are often described as "black boxes". In many real-world applications however, models may have to sacrifice predictive power in favour of human-interpretability. When this is the case, feature engineering becomes a…

Machine Learning · Statistics 2017-06-22 Gabriele Tolomei , Fabrizio Silvestri , Andrew Haines , Mounia Lalmas

A predictive model makes outcome predictions based on some given features, i.e., it estimates the conditional probability of the outcome given a feature vector. In general, a predictive model cannot estimate the causal effect of a feature…

Machine Learning · Computer Science 2023-04-11 Jiuyong Li , Lin Liu , Ziqi Xu , Ha Xuan Tran , Thuc Duy Le , Jixue Liu

Language models are commonly fine-tuned via reinforcement learning to alter their behavior or elicit new capabilities. Datasets used for these purposes, and particularly human preference datasets, are often noisy. The relatively small size…

Machine Learning · Computer Science 2025-07-22 Daniel Fein , Gabriela Aranguiz-Dias

The impact of machine learning models on healthcare will depend on the degree of trust that healthcare professionals place in the predictions made by these models. In this paper, we present a method to provide people with clinical expertise…

Machine Learning · Computer Science 2021-03-05 Aniruddh Raghu , John Guttag , Katherine Young , Eugene Pomerantsev , Adrian V. Dalca , Collin M. Stultz

Predictions about people, such as their expected educational achievement or their credit risk, can be performative and shape the outcome that they aim to predict. Understanding the causal effect of these predictions on the eventual outcomes…

Machine Learning · Statistics 2022-10-19 Celestine Mendler-Dünner , Frances Ding , Yixin Wang

Feature engineering is a crucial step in the process of predictive modeling. It involves the transformation of given feature space, typically using mathematical functions, with the objective of reducing the modeling error for a given…

Artificial Intelligence · Computer Science 2017-09-22 Udayan Khurana , Horst Samulowitz , Deepak Turaga

Data attribution, tracing a model's prediction back to specific training data, is an important tool for interpreting sophisticated AI models. The widely used TRAK algorithm addresses this challenge by first approximating the underlying…

Machine Learning · Computer Science 2026-02-03 Han Tong , Shubhangi Ghosh , Haolin Zou , Arian Maleki

Deep policy networks enable robots to learn behaviors to solve various real-world complex tasks in an end-to-end fashion. However, they lack transparency to provide the reasons of actions. Thus, such a black-box model often results in low…

Robotics · Computer Science 2023-10-31 Seongun Kim , Jaesik Choi

A variety of fairness constraints have been proposed in the literature to mitigate group-level statistical bias. Their impacts have been largely evaluated for different groups of populations corresponding to a set of sensitive attributes,…

Machine Learning · Computer Science 2022-07-01 Jialu Wang , Xin Eric Wang , Yang Liu

Latent force models are systems whereby there is a mechanistic model describing the dynamics of the system state, with some unknown forcing term that is approximated with a Gaussian process. If such dynamics are non-linear, it can be…

Machine Learning · Statistics 2019-11-05 Wil O. C. Ward , Tom Ryder , Dennis Prangle , Mauricio A. Álvarez

We consider the issue of assessing influence of observations in the class of Birnbaum-Saunders nonlinear regression models, which is useful in lifetime data analysis. Our results generalize those in Galea et al. [2004, Influence diagnostics…

Methodology · Statistics 2011-11-22 Artur J. Lemonte

Deploying machine learning models in safety-related do-mains (e.g. autonomous driving, medical diagnosis) demands for approaches that are explainable, robust against adversarial attacks and aware of the model uncertainty. Recent deep…

Computer Vision and Pattern Recognition · Computer Science 2020-12-14 Jan Kronenberger , Anselm Haselhoff

Recent advances in algorithmic design show how to utilize predictions obtained by machine learning models from past and present data. These approaches have demonstrated an enhancement in performance when the predictions are accurate, while…

Machine Learning · Computer Science 2024-03-13 Marek Elias , Haim Kaplan , Yishay Mansour , Shay Moran

Off-policy evaluation in reinforcement learning offers the chance of using observational data to improve future outcomes in domains such as healthcare and education, but safe deployment in high stakes settings requires ways of assessing its…

Machine Learning · Computer Science 2020-08-12 Omer Gottesman , Joseph Futoma , Yao Liu , Sonali Parbhoo , Leo Anthony Celi , Emma Brunskill , Finale Doshi-Velez

We aim to construct a class of learning algorithms that are of practical value to applied researchers in fields such as biostatistics, epidemiology and econometrics, where the need to learn from incompletely observed information is…

Methodology · Statistics 2021-02-09 Alicia Curth , Ahmed M. Alaa , Mihaela van der Schaar

With increasing reliance on the outcomes of black-box models in critical applications, post-hoc explainability tools that do not require access to the model internals are often used to enable humans understand and trust these models. In…

In model-based reinforcement learning, simulated experiences from the learned model are often treated as equivalent to experience from the real environment. However, when the model is inaccurate, it can catastrophically interfere with…

Machine Learning · Computer Science 2024-06-25 Erin J. Talvitie , Zilei Shao , Huiying Li , Jinghan Hu , Jacob Boerma , Rory Zhao , Xintong Wang

Can we preserve the accuracy of neural models while also providing faithful explanations of model decisions to training data? We propose a "wrapper box'' pipeline: training a neural model as usual and then using its learned feature…

Machine Learning · Computer Science 2024-10-07 Yiheng Su , Junyi Jessy Li , Matthew Lease

Interpretability has become incredibly important as machine learning is increasingly used to inform consequential decisions. We propose to construct global explanations of complex, blackbox models in the form of a decision tree…

Machine Learning · Computer Science 2019-01-28 Osbert Bastani , Carolyn Kim , Hamsa Bastani