English
Related papers

Related papers: Learning Coefficients in Semi-Regular Models

200 papers

Bayesian methods for graphical log-linear marginal models have not been developed in the same extent as traditional frequentist approaches. In this work, we introduce a novel Bayesian approach for quantitative learning for such models.…

Methodology · Statistics 2018-07-04 Ioannis Ntzoufras , Claudia Tarantola , Monia Lupparelli

Loss functions serve as the foundation of supervised learning and are often chosen prior to model development. To avoid potentially ad hoc choices of losses, statistical decision theory describes a desirable property for losses known as…

Machine Learning · Statistics 2023-11-30 Kevin Lam , Christian Walder , Spiridon Penev , Richard Nock

Few-shot learning is a rapidly evolving area of research in machine learning where the goal is to classify unlabeled data with only one or "a few" labeled exemplary samples. Neural networks are typically trained to minimize a distance…

Computer Vision and Pattern Recognition · Computer Science 2022-12-09 Samuel Hess , Gregory Ditzler

In this paper we investigate the problem of learning an unknown bounded function. We be emphasize special cases where it is possible to provide very simple (in terms of computation) estimates enjoying in addition the property of being…

Statistics Theory · Mathematics 2007-06-13 Gerard Kerkyacharian , Dominique Picard

We study problem-dependent rates, i.e., generalization errors that scale near-optimally with the variance, the effective loss, or the gradient norms evaluated at the "best hypothesis." We introduce a principled framework dubbed "uniform…

Machine Learning · Statistics 2020-12-25 Yunbei Xu , Assaf Zeevi

Gaussian latent tree models, or more generally, Gaussian latent forest models have Fisher-information matrices that become singular along interesting submodels, namely, models that correspond to subforests. For these singularities, we…

Methodology · Statistics 2015-12-24 Mathias Drton , Shaowei Lin , Luca Weihs , Piotr Zwiernik

We study the typical learning properties of the recently introduced Soft Margin Classifiers (SMCs), learning realizable and unrealizable tasks, with the tools of Statistical Mechanics. We derive analytically the behaviour of the learning…

Disordered Systems and Neural Networks · Physics 2009-11-07 Sebastian Risau-Gusman , Mirta B. Gordon

In statistical classification/multiple hypothesis testing and machine learning, a model distribution estimated from the training data is usually applied to replace the unknown true distribution in the Bayes decision rule, which introduces a…

Information Theory · Computer Science 2024-09-24 Zijian Yang , Vahe Eminyan , Ralf Schlüter , Hermann Ney

Multinomial mixtures are widely used in the information engineering field, however, their mathematical properties are not yet clarified because they are singular learning models. In fact, the models are non-identifiable and their Fisher…

Machine Learning · Computer Science 2022-03-15 Takumi Watanabe , Sumio Watanabe

We focus on a stochastic learning model where the learner observes a finite set of training examples and the output of the learning process is a data-dependent distribution over a space of hypotheses. The learned data-dependent distribution…

Machine Learning · Statistics 2020-12-29 Omar Rivasplata , Ilja Kuzborskij , Csaba Szepesvari , John Shawe-Taylor

In the problem of learning with label proportions, which we call LLP learning, the training data is unlabeled, and only the proportions of examples receiving each label are given. The goal is to learn a hypothesis that predicts the…

Machine Learning · Computer Science 2020-04-08 Benjamin Fish , Lev Reyzin

Pattern recognition is a central topic in Learning Theory with numerous applications such as voice and text recognition, image analysis, computer diagnosis. The statistical set-up in classification is the following: we are given an i.i.d.…

Quantum Physics · Physics 2011-06-23 Madalin Guta , Wojciech Kotlowski

To enhance the reproducibility and reliability of deep learning models, we address a critical gap in current training methodologies: the lack of mechanisms that ensure consistent and robust performance across runs. Our empirical analysis…

Machine Learning · Computer Science 2026-01-05 Waqas Ahmed , Sheeba Samuel , Kevin Coakley , Birgitta Koenig-Ries , Odd Erik Gundersen

Bayesian model selection commonly relies on Laplace approximation or the Bayesian Information Criterion (BIC), which assume that the effective model dimension equals the number of parameters. Singular learning theory replaces this…

Machine Learning · Statistics 2026-01-06 Kalyaan Rao

We study the problem of learning an unknown function using random feature models. Our main contribution is an exact asymptotic analysis of such learning problems with Gaussian data. Under mild regularity conditions for the feature matrix,…

Information Theory · Computer Science 2020-08-28 Oussama Dhifallah , Yue M. Lu

Determining the stability of molecules and condensed phases is the cornerstone of atomistic modelling, underpinning our understanding of chemical and materials properties and transformations. Here we show that a machine learning model,…

Learning curves provide insight into the dependence of a learner's generalization performance on the training set size. This important tool can be used for model selection, to predict the effect of more training data, and to reduce the…

Machine Learning · Computer Science 2022-11-08 Tom Viering , Marco Loog

All machine learning algorithms use a loss, cost, utility or reward function to encode the learning objective and oversee the learning process. This function that supervises learning is a frequently unrecognized hyperparameter that…

Neural and Evolutionary Computing · Computer Science 2024-11-06 Mathew Mithra Noel , Arindam Banerjee , Yug Oswal , Geraldine Bessie Amali D , Venkataraman Muthiah-Nakarajan

The property of learning-curve monotonicity, highlighted in a recent series of work by Loog, Mey and Viering, describes algorithms which only improve in average performance given more data, for any underlying data distribution within a…

Statistics Theory · Mathematics 2025-12-29 Mark Sellke , Steven Yin

In many scientific and data-driven applications, machine learning models are increasingly used as measurement instruments, rather than merely as predictors of predefined labels. When the measurement function is learned from data, the…

Machine Learning · Computer Science 2026-01-27 Indrė Žliobaitė