English
Related papers

Related papers: Performance-guaranteed regularization in maximum l…

200 papers

In machine learning, it is common to optimize the parameters of a probabilistic model, modulated by an ad hoc regularization term that penalizes some values of the parameters. Regularization terms appear naturally in Variational Inference,…

Machine Learning · Computer Science 2024-02-08 Pierre Wolinski , Guillaume Charpiat , Yann Ollivier

We discuss optimal prediction for families of probability distributions with a locally compact topological group structure. Right-invariant priors were previously shown to yield a posterior predictive distribution minimizing the worst-case…

Statistics Theory · Mathematics 2025-08-26 Jannis Bolik , Thomas Hofmann

The aim of this paper is to provide new theoretical and computational understanding on two loss regularizations employed in deep learning, known as local entropy and heat regularization. For both regularized losses we introduce variational…

Machine Learning · Statistics 2019-06-26 Nicolas Garcia Trillos , Zach Kaplan , Daniel Sanz-Alonso

Accurate probabilistic predictions are essential for optimal decision making. While neural network miscalibration has been studied primarily in classification, we investigate this in the less-explored domain of regression. We conduct the…

Machine Learning · Computer Science 2023-06-08 Victor Dheur , Souhaib Ben Taieb

We present algorithms for efficiently learning regularizers that improve generalization. Our approach is based on the insight that regularizers can be viewed as upper bounds on the generalization gap, and that reducing the slack in the…

Machine Learning · Computer Science 2019-02-25 Matthew Streeter

Understanding the role of regularization is a central question in Statistical Inference. Empirically, well-chosen regularization schemes often dramatically improve the quality of the inferred models by avoiding overfitting of the training…

Machine Learning · Computer Science 2022-05-25 Arnaud Fanthomme , F Rizzato , S Cocco , R Monasson

This paper introduces two new robust methods for estimation of parameters in a given parametric family. The first method is that of `minimum weighted L2', effectively minimising an estimate of the integrated (and possibly weighted) squared…

Methodology · Statistics 2026-02-23 Nils Lid Hjort

Proper scoring rules evaluate the quality of probabilistic predictions, playing an essential role in the pursuit of accurate and well-calibrated models. Every proper score decomposes into two fundamental components -- proper calibration…

Machine Learning · Computer Science 2023-12-15 Teodora Popordanoska , Sebastian G. Gruber , Aleksei Tiulpin , Florian Buettner , Matthew B. Blaschko

We address the image restoration problem under Poisson noise corruption. The Kullback-Leibler divergence, which is typically adopted in the variational framework as data fidelity term in this case, is coupled with the second-order Total…

Numerical Analysis · Mathematics 2022-05-27 Daniela di Serafino , Monica Pragliola

In binary classification tasks, accurate representation of probabilistic predictions is essential for various real-world applications such as predicting payment defaults or assessing medical risks. The model must then be well-calibrated to…

Machine Learning · Computer Science 2024-08-08 Agathe Fernandes Machado , Arthur Charpentier , Emmanuel Flachaire , Ewen Gallic , François Hu

The Kullback-Leibler divergence, the Kullback-Leibler variation, and the Bernstein "norm" are used to quantify discrepancies among probability distributions in likelihood models such as nonparametric maximum likelihood and nonparametric…

Statistics Theory · Mathematics 2026-01-27 Tetsuya Kaji

Consider the nonparametric logistic regression problem. In the logistic regression, we usually consider the maximum likelihood estimator, and the excess risk is the expectation of the Kullback-Leibler (KL) divergence between the true and…

Statistics Theory · Mathematics 2025-02-26 Atsutomo Yara , Yoshikazu Terada

Many imaging problems require solving an inverse problem that is ill-conditioned or ill-posed. Imaging methods typically address this difficulty by regularising the estimation problem to make it well-posed. This often requires setting the…

Methodology · Statistics 2020-08-17 Ana F. Vidal , Valentin De Bortoli , Marcelo Pereyra , Alain Durmus

The standard paradigm of neural language generation adopts maximum likelihood estimation (MLE) as the optimizing method. From a distributional view, MLE in fact minimizes the Kullback-Leibler divergence (KLD) between the distribution of the…

Computation and Language · Computer Science 2023-02-28 Haozhe Ji , Pei Ke , Zhipeng Hu , Rongsheng Zhang , Minlie Huang

From the statistical learning perspective, complexity control via explicit regularization is a necessity for improving the generalization of over-parameterized models. However, the impressive generalization performance of neural networks…

Machine Learning · Computer Science 2021-02-09 Taejong Joo , Uijung Chung

Regularization is a central tool for addressing ill-posedness in inverse problems and statistical estimation, with the choice of a suitable penalty often determining the reliability and interpretability of downstream solutions. While recent…

Optimization and Control · Mathematics 2025-10-07 Oscar Leong , Eliza O'Reilly , Yong Sheng Soh

Many mathematical imaging problems are posed as non-convex optimization problems. When numerically tractable global optimization procedures are not available, one is often interested in testing ex post facto whether or not a locally…

Signal Processing · Electrical Eng. & Systems 2020-07-13 Joel W. LeBlanc , Brian J. Thelen , Alfred O. Hero

Maximum likelihood estimation is a common method of estimating the parameters of the probability distribution from a given sample. This paper aims to introduce the maximum likelihood estimation in the framework of sublinear expectation. We…

Probability · Mathematics 2023-01-16 Xinpeng Li , Yue Liu , Jiaquan Lu

In this work, we introduce a novel estimator of the predictive risk with Poisson data, when the loss function is the Kullback-Leibler divergence, in order to define a regularization parameter's choice rule for the Expectation Maximization…

Numerical Analysis · Mathematics 2021-05-26 Paolo Massa , Federico Benvenuto

We consider the fundamental problem of estimating a discrete distribution on a domain of size $K$ with high probability in Kullback-Leibler divergence. We provide upper and lower bounds on the minimax estimation rate, which show that the…

Machine Learning · Statistics 2026-02-23 Dirk van der Hoeven , Julia Olkhovskaia , Tim van Erven