English
Related papers

Related papers: Beyond Top-Class Agreement: Using Divergences to F…

200 papers

The problem of detecting whether a test sample is from in-distribution (i.e., training distribution by a classifier) or out-of-distribution sufficiently different from it arises in many real-world machine learning applications. However, the…

Machine Learning · Statistics 2018-02-27 Kimin Lee , Honglak Lee , Kibok Lee , Jinwoo Shin

Many real-world classification problems are significantly class-imbalanced to detriment of the class of interest. The standard set of proper evaluation metrics is well-known but the usual assumption is that the test dataset imbalance equals…

Machine Learning · Computer Science 2020-04-16 Jan Brabec , Tomáš Komárek , Vojtěch Franc , Lukáš Machlica

A multitude of classifiers can be trained on the same data to achieve similar performances during test time, while having learned significantly different classification patterns. This phenomenon, which we call prediction discrepancies, is…

Machine Learning · Computer Science 2024-08-01 Xavier Renard , Thibault Laugel , Marcin Detyniecki

In the real world, a learning system could receive an input that is unlike anything it has seen during training. Unfortunately, out-of-distribution samples can lead to unpredictable behaviour. We need to know whether any given input belongs…

Machine Learning · Computer Science 2019-08-21 Alireza Shafaei , Mark Schmidt , James J. Little

In this work, the probability of an event under some joint distribution is bounded by measuring it with the product of the marginals instead (which is typically easier to analyze) together with a measure of the dependence between the two…

Information Theory · Computer Science 2020-10-22 Amedeo Roberto Esposito , Michael Gastpar , Ibrahim Issa

The performance of machine learning models relies heavily on the quality of input data, yet real-world applications often face significant data-related challenges. A common issue arises when curating training data or deploying models: two…

Machine Learning · Computer Science 2025-09-24 Varun Babbar , Zhicheng Guo , Cynthia Rudin

There are three classical divergence measures exist in the literature on information theory and statistics. These are namely, Jeffryes-Kullback-Leiber J-divergence. Sibson-Burbea-Rao Jensen-Shannon divegernce and Taneja Arithmetic-Geometric…

Information Theory · Computer Science 2011-04-01 Inder Jeet Taneja

In satellite image analysis, distributional mismatch between the training and test data may arise due to several reasons, including unseen classes in the test data and differences in the geographic area. Deep learning based models may…

Machine Learning · Computer Science 2021-04-13 Jakob Gawlikowski , Sudipan Saha , Anna Kruspe , Xiao Xiang Zhu

When facing uncertainty, decision-makers want predictions they can trust. A machine learning provider can convey confidence to decision-makers by guaranteeing their predictions are distribution calibrated -- amongst the inputs that receive…

Machine Learning · Statistics 2021-07-14 Shengjia Zhao , Michael P. Kim , Roshni Sahoo , Tengyu Ma , Stefano Ermon

Machine learning models are increasingly trained or fine-tuned on synthetic data. Recursively training on such data has been observed to significantly degrade performance in a wide range of tasks, often characterized by a progressive drift…

Machine Learning · Statistics 2026-02-19 Nail B. Khelifa , Richard E. Turner , Ramji Venkataramanan

There are many information and divergence measures exist in the literature on information theory and statistics. The most famous among them are Kullback-Leibler (1951) relative information and Jeffreys (1951) J-divergence. Sibson (1969)…

Probability · Mathematics 2007-05-23 Inder Jeet Taneja

The inability of Machine Learning (ML) models to successfully extrapolate correct predictions from out-of-distribution (OoD) samples is a major hindrance to the application of ML in critical applications. Until the generalization ability of…

Computer Vision and Pattern Recognition · Computer Science 2020-04-01 Mark Philip Philipsen , Thomas Baltzer Moeslund

For machine learning systems to be reliable, we must understand their performance in unseen, out-of-distribution environments. In this paper, we empirically show that out-of-distribution performance is strongly correlated with…

Estimation of the $\phi$-divergence between two unknown probability distributions using empirical data is a fundamental problem in information theory and statistical learning. We consider a multi-variate generalization of the data dependent…

Probability · Mathematics 2018-01-04 Fengqiao Luo , Sanjay Mehrotra

We examine the estimation of the Kullback-Leibler (KL) divergence and the use of the goodness-of-fit test for multivariate continuous distributions. Our starting point is the maximum entropy principle for Shannon entropy: among all…

Statistics Theory · Mathematics 2026-03-10 Mehmet Siddik Cadirci , Martin Singull

An interesting phenomenon arises: Empirical Risk Minimization (ERM) sometimes outperforms methods specifically designed for out-of-distribution tasks. This motivates an investigation into the reasons behind such behavior beyond algorithmic…

Machine Learning · Computer Science 2026-01-21 Hong Zheng , Fei Teng

An initial screening experiment may lead to ambiguous conclusions regarding the factors which are active in explaining the variation of an outcome variable: thus adding follow-up runs becomes necessary. We propose a fully Bayes objective…

Methodology · Statistics 2014-05-13 Guido Consonni , Laura Deldossi

Distribution shift occurs when the test distribution differs from the training distribution, and it can considerably degrade performance of machine learning models deployed in the real world. Temporal shifts -- distribution shifts arising…

Machine Learning · Computer Science 2023-01-18 Huaxiu Yao , Caroline Choi , Bochuan Cao , Yoonho Lee , Pang Wei Koh , Chelsea Finn

Temperature sampling is a conventional approach to diversify large language model predictions. As temperature increases, the prediction becomes diverse but also vulnerable to hallucinations -- generating tokens that are sensible but not…

Computation and Language · Computer Science 2023-12-01 Chung-Ching Chang , David Reitter , Renat Aksitov , Yun-Hsuan Sung

Reliable and accurate estimation of the error of an ML model in unseen test domains is an important problem for safe intelligent systems. Prior work uses disagreement discrepancy (DIS^2) to derive practical error bounds under distribution…

Machine Learning · Computer Science 2025-06-19 Aayush Mishra , Anqi Liu
‹ Prev 1 3 4 5 6 7 10 Next ›