English
Related papers

Related papers: On Information Regularization

200 papers

Recent advances in weakly supervised classification allow us to train a classifier only from positive and unlabeled (PU) data. However, existing PU classification methods typically require an accurate estimate of the class-prior…

Machine Learning · Statistics 2022-06-22 Tomoya Sakai , Gang Niu , Masashi Sugiyama

Physics-informed statistical learning (PISL) integrates empirical data with physical knowledge to enhance the statistical performance of estimators. While PISL methods are widely used in practice, a comprehensive theoretical understanding…

Machine Learning · Statistics 2025-10-28 Diego Marcondes

Linear discrimination, from the point of view of numerical linear algebra, can be treated as solving an ill-posed system of linear equations. In order to generate a solution that is robust in the presence of noise, these problems require…

Genomics · Quantitative Biology 2007-05-23 Erik Andries , Thomas Hagstrom , Susan R. Atlas , Cheryl Willman

We consider semi-supervised classification when part of the available data is unlabeled. These unlabeled data can be useful for the classification problem when we make an assumption relating the behavior of the regression function to that…

Statistics Theory · Mathematics 2007-06-13 Philippe Rigollet

This paper presents an error analysis of classical and learned Tikhonov regularization schemes for inverse problems. We first demonstrate, both theoretically and numerically, that using a fixed regularization parameter across varying noise…

Numerical Analysis · Mathematics 2026-04-02 Arne Behrens , Meira Iske , Ming Jiang , Peter Maass , Sebastian Neumayer

In this work, we introduce a novel approach to regularization in multivariable regression problems. Our regularizer, called DLoss, penalises differences between the model's derivatives and derivatives of the data generating function as…

Machine Learning · Computer Science 2024-05-02 Enrico Lopedoto , Maksim Shekhunov , Vitaly Aksenov , Kizito Salako , Tillman Weyde

Invariant Causal Prediction (Peters et al., 2016) is a technique for out-of-distribution generalization which assumes that some aspects of the data distribution vary across the training set but that the underlying causal mechanisms remain…

Machine Learning · Computer Science 2021-03-30 Elan Rosenfeld , Pradeep Ravikumar , Andrej Risteski

Fast accumulation of large amounts of complex data has created a need for more sophisticated statistical methodologies to discover interesting patterns and better extract information from these data. The large scale of the data often…

Methodology · Statistics 2014-09-09 Yuliya Marchetti , Qing Zhou

We propose a novel method for modeling data by using structural models based on economic theory as regularizers for statistical models. We show that even if a structural model is misspecified, as long as it is informative about the…

Econometrics · Economics 2020-06-15 Jiaming Mao , Zhesheng Zheng

Over-parameterized deep models usually over-fit to a given training distribution, which makes them sensitive to small changes and out-of-distribution samples at inference time, leading to low generalization performance. To this end, several…

Computer Vision and Pattern Recognition · Computer Science 2019-12-12 Saeid Asgari Taghanaki , Kumar Abhishek , Ghassan Hamarneh

Axiomatic information retrieval (IR) seeks a set of principle properties desirable in IR models. These properties when formally expressed provide guidance in the search for better relevance estimation functions. Neural ranking models…

Information Retrieval · Computer Science 2019-04-16 Corby Rosset , Bhaskar Mitra , Chenyan Xiong , Nick Craswell , Xia Song , Saurabh Tiwary

Regularization, whether explicit in terms of a penalty in the loss or implicit in the choice of algorithm, is a cornerstone of modern machine learning. Indeed, controlling the complexity of the model class is particularly important when…

Machine Learning · Statistics 2024-10-22 Matteo Vilucchio , Nikolaos Tsilivis , Bruno Loureiro , Julia Kempe

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

Training deep neural networks is known to require a large number of training samples. However, in many applications only few training samples are available. In this work, we tackle the issue of training neural networks for classification…

Machine Learning · Computer Science 2017-12-25 Soufiane Belharbi , Clément Chatelain , Romain Hérault , Sébastien Adam

We propose a novel framework to perform classification via deep learning in the presence of noisy annotations. When trained on noisy labels, deep neural networks have been observed to first fit the training data with clean labels during an…

Machine Learning · Computer Science 2020-10-26 Sheng Liu , Jonathan Niles-Weed , Narges Razavian , Carlos Fernandez-Granda

This paper explores Bayesian estimation for categorical data, focusing on simple yet effective models that provide a foundation for applying more advanced methods accurately and reliably in real-world applications. We begin by revisiting…

Methodology · Statistics 2025-09-03 Jan Kalina

Multiclass classification problems such as image annotation can involve a large number of classes. In this context, confusion between classes can occur, and single label classification may be misleading. We provide in the present paper a…

Statistics Theory · Mathematics 2017-12-19 Christophe Denis , Mohamed Hebiri

Many classification problems involve data instances that are interlinked with each other, such as webpages connected by hyperlinks. Techniques for "collective classification" (CC) often increase accuracy for such data graphs, but usually…

Machine Learning · Computer Science 2012-07-03 Luke McDowell , David Aha

Data augmentation is used in machine learning to make the classifier invariant to label-preserving transformations. Usually this invariance is only encouraged implicitly by including a single augmented input during training. However,…

Machine Learning · Computer Science 2022-03-08 Aleksander Botev , Matthias Bauer , Soham De

Information theory is built on probability measures and by definition a probability measure has total mass 1. Probability measures are used to model uncertainty, and one may ask how important it is that the total mass is one. We claim that…

Information Theory · Computer Science 2022-02-08 Peter Harremoës