English
Related papers

Related papers: Generative Perturbation Analysis for Probabilistic…

200 papers

Out-of-distribution (OOD) detection aims to identify inputs that differ from the training distribution in order to reduce unreliable predictions by deep neural networks. Among post-hoc feature-space approaches, OOD detection is commonly…

Machine Learning · Computer Science 2026-03-25 Mohamed Bahi Yahiaoui , Geoffrey Daniel , Loïc Giraldi , Jérémie Bruyelle , Julyan Arbel

Generative models, like large language models, are becoming increasingly relevant in our daily lives, yet a theoretical framework to assess their generalization behavior and uncertainty does not exist. Particularly, the problem of…

Machine Learning · Computer Science 2024-07-11 Sebastian G. Gruber , Florian Buettner

Detecting anomalies in large sets of observations is crucial in various applications, such as epidemiological studies, gene expression studies, and systems monitoring. We consider settings where the units of interest result in multiple…

Methodology · Statistics 2025-12-22 Ivo V. Stoepker , Rui M. Castro , Ery Arias-Castro

In the context of machine learning, disparate impact refers to a form of systematic discrimination whereby the output distribution of a model depends on the value of a sensitive attribute (e.g., race or gender). In this paper, we propose an…

Information Theory · Computer Science 2018-05-14 Hao Wang , Berk Ustun , Flavio P. Calmon

Score-based diffusion models generate samples from an unknown target distribution using a time-reversed diffusion process. While such models represent state-of-the-art approaches in industrial applications such as artificial image…

Machine Learning · Computer Science 2026-02-09 Adrian Baule

Anomaly detection (AD) plays a pivotal role across diverse domains, including cybersecurity, finance, healthcare, and industrial manufacturing, by identifying unexpected patterns that deviate from established norms in real-world data.…

Machine Learning · Computer Science 2025-06-12 Yang Liu , Jing Liu , Chengfang Li , Rui Xi , Wenchao Li , Liang Cao , Jin Wang , Laurence T. Yang , Junsong Yuan , Wei Zhou

We explore the methodology and theory of reward-directed generation via conditional diffusion models. Directed generation aims to generate samples with desired properties as measured by a reward function, which has broad applications in…

Machine Learning · Computer Science 2023-07-17 Hui Yuan , Kaixuan Huang , Chengzhuo Ni , Minshuo Chen , Mengdi Wang

In this paper we present a study of anomalous diffusion using a Fokker-Planck description with fractional velocity derivatives. The distribution functions are found using numerical means for varying degree of fractionality observing the…

Plasma Physics · Physics 2014-12-18 Johan Anderson , Eun-jin Kim , Sara Moradi

While the Graybox characterization method allows for implicit noise models and is platform-agnostic, the method lacks uncertainty quantification. Characterization of quantum devices is a crucial process that enables researchers to gain…

Quantum Physics · Physics 2025-09-30 Poramet Pathumsoot , Michal Hajdušek , Rodney Van Meter

Key doctrines, including novelty (patent), originality (copyright), and distinctiveness (trademark), turn on a shared empirical question: whether a body of work is meaningfully distinct from a relevant reference class. Yet analyses…

Computers and Society · Computer Science 2026-01-27 Anirban Mukherjee , Hannah Hanwen Chang

Deep neural networks (DNNs) have demonstrated remarkable success, yet their wide adoption is often hindered by their opaque decision-making. To address this, attribution methods have been proposed to assign relevance values to each part of…

Computer Vision and Pattern Recognition · Computer Science 2025-04-10 Danielle Cohen , Hila Chefer , Lior Wolf

Many parametric statistical models are not properly normalised and only specified up to an intractable partition function, which renders parameter estimation difficult. Examples of unnormalised models are Gibbs distributions, Markov random…

Machine Learning · Statistics 2018-06-12 Ciwan Ceylan , Michael U. Gutmann

Gaussian process regression is widely applied in computational science and engineering for surrogate modeling owning to its kernel-based and probabilistic nature. In this work, we propose a Bayesian approach that integrates the variability…

Machine Learning · Computer Science 2025-01-03 Dongwei Ye , Weihao Yan , Christoph Brune , Mengwu Guo

To advance the transparency of learning machines such as Deep Neural Networks (DNNs), the field of Explainable AI (XAI) was established to provide interpretations of DNNs' predictions. While different explanation techniques exist, a popular…

The advent of Generative Artificial Intelligence (GAI) has heralded an inflection point that changed how society thinks about knowledge acquisition. While GAI cannot be fully trusted for decision-making, it may still provide valuable…

Methodology · Statistics 2025-05-20 Sean O'Hagan , Veronika Ročková

We propose an efficient framework for amortized conditional inference by leveraging exact conditional score-guided diffusion models to train a non-reversible neural network as a conditional generative model. Traditional normalizing flow…

Computational Engineering, Finance, and Science · Computer Science 2025-06-24 Zezhong Zhang , Caroline Tatsuoka , Dongbin Xiu , Guannan Zhang

Anomaly detection is being regarded as an unsupervised learning task as anomalies stem from adversarial or unlikely events with unknown distributions. However, the predictive performance of purely unsupervised anomaly detection often fails…

Machine Learning · Computer Science 2014-01-27 Nico Goernitz , Marius Micha Kloft , Konrad Rieck , Ulf Brefeld

Feature attribution analysis is critical for interpreting machine learning models and supporting reliable data-driven decisions. However, feature attribution measures often exhibit stochastic variation: different train--test splits, random…

Machine Learning · Statistics 2026-05-15 Lanxin Xiang , Liang Shi , Youhui Ye , Boyu Jiang , Dawei Zhou , Feng Guo

Most methods in explainable AI (XAI) focus on providing reasons for the prediction of a given set of features. However, we solve an inverse explanation problem, i.e., given the deviation of a label, find the reasons of this deviation. We…

Machine Learning · Computer Science 2024-11-06 Quan Long

Motivated by undetectable risks in generative AI, we study a general robust aggregation problem: how to aggregate several probability distributions to boost safety. We present consensus sampling, a black-box algorithm that, given k…

Artificial Intelligence · Computer Science 2026-05-12 Adam Tauman Kalai , Yael Tauman Kalai , Or Zamir