English
Related papers

Related papers: Amplifying Inter-message Distance: On Information …

200 papers

The concept of Label Distribution Learning (LDL) is a technique to stabilize classification and regression problems with ambiguous and/or imbalanced labels. A prototypical use-case of LDL is human age estimation based on profile images.…

Machine Learning · Computer Science 2022-09-07 Maurice Günder , Nico Piatkowski , Christian Bauckhage

This short note is on a property of the Kullback-Leibler (KL) divergence which indicates that independent Gaussian distributions minimize the KL divergence from given independent Gaussian distributions. The primary purpose of this note is…

Information Theory · Computer Science 2020-12-04 Song Fang , Quanyan Zhu

We interpret likelihood-based test functions from a geometric perspective where the Kullback-Leibler (KL) divergence is adopted to quantify the distance from a distribution to another. Such a test function can be seen as a sub-Gaussian…

Information Theory · Computer Science 2021-01-05 Yan Wang

We define Persistent Mutual Information (PMI) as the Mutual (Shannon) Information between the past history of a system and its evolution significantly later in the future. This quantifies how much past observations enable long term…

Adaptation and Self-Organizing Systems · Physics 2015-03-13 R. C. Ball , M. Diakonova , R. S. MacKay

We revisit extending the Kolmogorov-Smirnov distance between probability distributions to the multidimensional setting and make new arguments about the proper way to approach this generalization. Our proposed formulation maximizes the…

Computation · Statistics 2025-04-16 Peter Matthew Jacobs , Foad Namjoo , Jeff M. Phillips

In many real-world applications, a model provider provides probabilistic forecasts to downstream decision-makers who use them to make decisions under diverse payoff objectives. The provider may have access to multiple predictive models,…

Machine Learning · Computer Science 2026-02-03 Yiding Feng , Liuhan Qian , Wei Tang

For a multinomial distribution, suppose that we have prior knowledge of the sum of the probabilities of some categories. This allows us to construct a submodel in a full (i.e., no-restriction) model. Maximum likelihood estimation (MLE)…

Statistics Theory · Mathematics 2021-06-07 Yo Sheena

It is well known that in Information Theory and Machine Learning the Kullback-Leibler divergence, which extends the concept of Shannon entropy, plays a fundamental role. Given an {\it a priori} probability kernel $\hat{\nu}$ and a…

Dynamical Systems · Mathematics 2021-06-04 Artur O. Lopes , Jairo K. Mengue

Recognizing subtle historical patterns is central to modeling and forecasting problems in time series analysis. Here we introduce and develop a new approach to quantify deviations in the underlying hidden generators of observed data…

Machine Learning · Statistics 2019-10-09 Yi Huang , Ishanu Chattopadhyay

Estimating the Kullback--Leibler (KL) divergence between language models has many applications, e.g., reinforcement learning from human feedback (RLHF), interpretability, and knowledge distillation. However, computing the exact KL…

Computation and Language · Computer Science 2025-10-28 Afra Amini , Tim Vieira , Ryan Cotterell

We derive a deterministic, non-asymptotic upper bound on the Kullback-Leibler (KL) divergence of the flow-matching distribution approximation. In particular, if the $L_2$ flow-matching loss is bounded by $\epsilon^2 > 0$, then the KL…

Machine Learning · Computer Science 2025-11-10 Maojiang Su , Jerry Yao-Chieh Hu , Sophia Pi , Han Liu

Outliers are ubiquitous in modern data sets. Distance-based techniques are a popular non-parametric approach to outlier detection as they require no prior assumptions on the data generating distribution and are simple to implement. Scaling…

Machine Learning · Statistics 2016-05-04 Mario Lucic , Olivier Bachem , Andreas Krause

We study a generalized version of Wyner's common information problem (also coined the distributed source simulation problem). The original common information problem consists in understanding the minimum rate of the common input to…

Information Theory · Computer Science 2019-12-04 Lei Yu , Vincent Y. F. Tan

Generative models have achieved remarkable success across a range of applications, yet their evaluation still lacks principled uncertainty quantification. In this paper, we develop a method for comparing how close different generative…

Machine Learning · Statistics 2025-10-24 Zijun Gao , Yan Sun , Han Su

The Maximum Mutual Information (MMI) criterion is different from the Least Error Rate (LER) criterion. It can reduce failing to report small probability events. This paper introduces the Channels Matching (CM) algorithm for the MMI…

Machine Learning · Computer Science 2019-01-30 Chenguang Lu

Four problems related to information divergence measures defined on finite alphabets are considered. In three of the cases we consider, we illustrate a contrast which arises between the binary-alphabet and larger-alphabet settings. This is…

Information Theory · Computer Science 2016-11-17 Jiantao Jiao , Thomas Courtade , Albert No , Kartik Venkat , Tsachy Weissman

The goal of most subjective studies is to place a set of stimuli on a perceptual scale. This is mostly done directly by rating, e.g. using single or double stimulus methodologies, or indirectly by ranking or pairwise comparison. All these…

Neurons and Cognition · Quantitative Biology 2022-03-25 Pastor Andréas , Lukáš Krasula , Xiaoqing Zhu , Zhi Li , Patrick Le Callet

Two-sample hypothesis testing-determining whether two sets of data are drawn from the same distribution-is a fundamental problem in statistics and machine learning with broad scientific applications. In the context of nonparametric testing,…

Machine Learning · Statistics 2026-04-21 Antoine Chatalic , Marco Letizia , Nicolas Schreuder , Lorenzo Rosasco

This paper studies the problem of interacting multiple model (IMM) estimation for jump Markov linear systems with unknown measurement noise covariance. The system state and the unknown covariance are jointly estimated in the framework of…

Systems and Control · Computer Science 2014-11-06 Wenling Li , Yingmin Jia

We present two classes of improved estimators for mutual information $M(X,Y)$, from samples of random points distributed according to some joint probability density $\mu(x,y)$. In contrast to conventional estimators based on binnings, they…

Statistical Mechanics · Physics 2009-11-10 Alexander Kraskov , Harald Stoegbauer , Peter Grassberger
‹ Prev 1 8 9 10 Next ›