English
Related papers

Related papers: A Generalized Bias-Variance Decomposition for Breg…

200 papers

Reliably estimating the uncertainty of a prediction throughout the model lifecycle is crucial in many safety-critical applications. The most common way to measure this uncertainty is via the predicted confidence. While this tends to work…

Machine Learning · Computer Science 2023-04-24 Sebastian G. Gruber , Florian Buettner

Bias-variance decompositions are widely used to understand the generalization performance of machine learning models. While the squared error loss permits a straightforward decomposition, other loss functions - such as zero-one loss or…

Machine Learning · Computer Science 2026-01-27 Tom Heskes

We introduce a novel bias-variance decomposition for a range of strictly convex margin losses, including the logistic loss (minimized by the classic LogitBoost algorithm), as well as the squared margin loss and canonical boosting loss.…

Machine Learning · Statistics 2022-04-27 Danny Wood , Tingting Mu , Gavin Brown

Bregman divergences generalize measures such as the squared Euclidean distance and the KL divergence, and arise throughout many areas of machine learning. In this paper, we focus on the problem of approximating an arbitrary Bregman…

Machine Learning · Statistics 2020-11-04 Ali Siahkamari , Xide Xia , Venkatesh Saligrama , David Castanon , Brian Kulis

Classical learning theory suggests that the optimal generalization performance of a machine learning model should occur at an intermediate model complexity, with simpler models exhibiting high bias and more complex models exhibiting high…

Machine Learning · Statistics 2020-11-09 Ben Adlam , Jeffrey Pennington

Adversarially trained models exhibit a large generalization gap: they can interpolate the training set even for large perturbation radii, but at the cost of large test error on clean samples. To investigate this gap, we decompose the test…

Machine Learning · Computer Science 2021-06-15 Yaodong Yu , Zitong Yang , Edgar Dobriban , Jacob Steinhardt , Yi Ma

This paper builds upon the work of Pfau (2013), which generalized the bias variance tradeoff to any Bregman divergence loss function. Pfau (2013) showed that for Bregman divergences, the bias and variances are defined with respect to a…

Machine Learning · Statistics 2022-02-11 Ben Adlam , Neha Gupta , Zelda Mariet , Jamie Smith

Classical wisdom in machine learning holds that the generalization error can be decomposed into bias and variance, and these two terms exhibit a \emph{trade-off}. However, in this paper, we show that for an ensemble of deep learning based…

Machine Learning · Computer Science 2023-10-16 Lin Chen , Michal Lukasik , Wittawat Jitkrittum , Chong You , Sanjiv Kumar

The problem to maximize the information divergence from an exponential family is generalized to the setting of Bregman divergences and suitably defined Bregman families.

Information Theory · Computer Science 2021-11-02 Johannes Rauh , František Matúš

Ensemble algorithms offer state of the art performance in many machine learning applications. A common explanation for their excellent performance is due to the bias-variance decomposition of the mean squared error which shows that the…

Machine Learning · Computer Science 2020-12-10 Sebastian Buschjäger , Lukas Pfahler , Katharina Morik

As large language models (LLMs) gain popularity in conducting prediction tasks in-context, understanding the sources of uncertainty in in-context learning becomes essential to ensuring reliability. The recent hypothesis of in-context…

Machine Learning · Statistics 2025-12-08 I. Shavindra Jayasekera , Jacob Si , Filippo Valdettaro , Wenlong Chen , A. Aldo Faisal , Yingzhen Li

This paper discusses basic results and recent developments on variational regularization methods, as developed for inverse problems. In a typical setup we review basic properties needed to obtain a convergent regularization scheme and…

Machine Learning · Computer Science 2021-12-10 Martin Burger

From the sampling of data to the initialisation of parameters, randomness is ubiquitous in modern Machine Learning practice. Understanding the statistical fluctuations engendered by the different sources of randomness in prediction is…

Machine Learning · Statistics 2022-10-03 Bruno Loureiro , Cédric Gerbelot , Maria Refinetti , Gabriele Sicuro , Florent Krzakala

A class of distortions termed functional Bregman divergences is defined, which includes squared error and relative entropy. A functional Bregman divergence acts on functions or distributions, and generalizes the standard Bregman divergence…

Information Theory · Computer Science 2007-07-13 B. A. Frigyik , S. Srivastava , M. R. Gupta

Bregman divergences play a central role in the design and analysis of a range of machine learning algorithms. This paper explores the use of Bregman divergences to establish reductions between such algorithms and their analyses. We present…

Machine Learning · Computer Science 2016-07-04 Richard Nock , Aditya Krishna Menon , Cheng Soon Ong

Prediction error is critical to assessing the performance of statistical methods and selecting statistical models. We propose the cross-validation and approximated cross-validation methods for estimating prediction error under a broad…

Statistics Theory · Mathematics 2007-06-13 Jianqing Fan , Chunming Zhang

We give a decomposition of the posterior predictive variance using the law of total variance and conditioning on a finite dimensional discrete random variable. This random variable summarizes various features of modeling that are used to…

Methodology · Statistics 2022-09-02 Dean Dustin , Bertrand Clarke

The paper introduces scaled Bregman distances of probability distributions which admit non-uniform contributions of observed events. They are introduced in a general form covering not only the distances of discrete and continuous stochastic…

Information Theory · Computer Science 2021-05-12 Wolfgang Stummer , Igor Vajda

Bias - variance decomposition of the expected error defined for regression and classification problems is an important tool to study and compare different algorithms, to find the best areas for their application. Here the decomposition is…

Machine Learning · Computer Science 2011-09-27 Marina Sapir

A Bayesian treatment of deep learning allows for the computation of uncertainties associated with the predictions of deep neural networks. We show how the concept of Errors-in-Variables can be used in Bayesian deep regression to also…

Machine Learning · Computer Science 2023-05-15 Jörg Martin , Clemens Elster
‹ Prev 1 2 3 10 Next ›