English
Related papers

Related papers: Extrapolating from neural network models: a cautio…

200 papers

A common strategy to train deep neural networks (DNNs) is to use very large architectures and to train them until they (almost) achieve zero training error. Empirically observed good generalization performance on test data, even in the…

Machine Learning · Statistics 2021-07-26 Nicole Mücke , Ingo Steinwart

Prediction accuracy and model explainability are the two most important objectives when developing machine learning algorithms to solve real-world problems. The neural networks are known to possess good prediction performance, but lack of…

Machine Learning · Statistics 2019-09-04 Zebin Yang , Aijun Zhang , Agus Sudjianto

Predictions of nuclear properties far from measured data are inherently imprecise because of uncertainties in our knowledge of nuclear forces and in our treatment of quantum many-body effects in strongly-interacting systems. While the model…

Nuclear Theory · Physics 2022-09-14 Rodrigo Navarro Perez , Nicolas Schunck

Optimization results are one method for understanding neural computation from Nature's perspective and for defining the physical limits on neuron-like engineering. Earlier work looks at individual properties or performance criteria and…

Neurons and Cognition · Quantitative Biology 2017-12-21 William B Levy , Toby Berger , Mustafa Sungkar

For a class of parametric modal regression models with measurement error, a simulation extrapolation estimation procedure is proposed in this paper for estimating the modal regression coefficients. Large sample properties of the proposed…

Methodology · Statistics 2019-10-04 Jianhong Shi , Yujing Zhang , Ping Yu , Weixing Song

Neural networks are able to approximate any continuous function on a compact set. However, it is not obvious how to quantify the error of the neural network, i.e., the remaining bias between the function and the neural network. Here, we…

Machine Learning · Statistics 2025-11-04 Gero Junike , Marco Oesting

Uncertainty estimation for machine learning models is of high importance in many scenarios such as constructing the confidence intervals for model predictions and detection of out-of-distribution or adversarially generated points. In this…

Machine Learning · Computer Science 2022-05-06 Kirill Fedyanin , Evgenii Tsymbalov , Maxim Panov

We propose and investigate new complementary methodologies for estimating predictive variance networks in regression neural networks. We derive a locally aware mini-batching scheme that result in sparse robust gradients, and show how to…

Machine Learning · Statistics 2019-11-05 Nicki S. Detlefsen , Martin Jørgensen , Søren Hauberg

Ensemble models can be used to estimate prediction uncertainties in machine learning models. However, an ensemble of N models is approximately N times more computationally demanding compared to a single model when it is used for inference.…

Machine Learning · Computer Science 2026-03-04 Vidit Agrawal , Shixin Zhang , Lane E. Schultz , Dane Morgan

Neural network potentials (NNPs) combine the computational efficiency of classical interatomic potentials with the high accuracy and flexibility of the ab initio methods used to create the training set, but can also result in unphysical…

Materials Science · Physics 2022-01-24 Leonid Kahle , Federico Zipoli

Neural networks are surprisingly good at interpolating and perform remarkably well when the training set examples resemble those in the test set. However, they are often unable to extrapolate patterns beyond the seen data, even when the…

Machine Learning · Computer Science 2020-04-23 Yann Dubois , Gautier Dagan , Dieuwke Hupkes , Elia Bruni

Extrapolation methods use the last few iterates of an optimization algorithm to produce a better estimate of the optimum. They were shown to achieve optimal convergence rates in a deterministic setting using simple gradient iterates. Here,…

Optimization and Control · Mathematics 2017-08-04 Damien Scieur , Alexandre d'Aspremont , Francis Bach

Neural network pruning is a popular technique used to reduce the inference costs of modern, potentially overparameterized, networks. Starting from a pre-trained network, the process is as follows: remove redundant parameters, retrain, and…

Machine Learning · Computer Science 2021-03-05 Lucas Liebenwein , Cenk Baykal , Brandon Carter , David Gifford , Daniela Rus

Probabilistic models often use neural networks to control their predictive uncertainty. However, when making out-of-distribution (OOD)} predictions, the often-uncontrollable extrapolation properties of neural networks yield poor uncertainty…

Machine Learning · Computer Science 2022-01-19 Pierre Segonne , Yevgen Zainchkovskyy , Søren Hauberg

Even when neural networks are widely used in a large number of applications, they are still considered as black boxes and present some difficulties for dimensioning or evaluating their prediction error. This has led to an increasing…

Machine Learning · Statistics 2021-05-11 Pablo Morala , Jenny Alexandra Cifuentes , Rosa E. Lillo , Iñaki Ucar

The common practice for displaying error bars on distributions of numbers of events is confusing and can lead to incorrect conclusions. A proposal is made for a different style of presentation that more directly indicates the level of…

Data Analysis, Statistics and Probability · Physics 2012-01-31 Ritu Aggarwal , Allen Caldwell

While neural networks have been successfully applied to many natural language processing tasks, they come at the cost of interpretability. In this paper, we propose a general methodology to analyze and interpret decisions from a neural…

Computation and Language · Computer Science 2017-01-11 Jiwei Li , Will Monroe , Dan Jurafsky

Neural networks are becoming an increasingly important tool in applications. However, neural networks are not widely used in statistical genetics. In this paper, we propose a new neural networks method called expectile neural networks. When…

Statistics Theory · Mathematics 2020-11-04 Jinghang Lin , Xiaoxi Shen , Qing Lu

Many common estimators in machine learning and causal inference are linear smoothers, where the prediction is a weighted average of the training outcomes. Some estimators, such as ordinary least squares and kernel ridge regression, allow…

Machine Learning · Computer Science 2026-04-02 David Arbour , Harsh Parikh , Bijan Niknam , Elizabeth Stuart , Kara Rudolph , Avi Feller

While neural networks can be trained to map from one specific dataset to another, they usually do not learn a generalized transformation that can extrapolate accurately outside the space of training. For instance, a generative adversarial…

Quantitative Methods · Quantitative Biology 2019-01-25 Matthew Amodio , David van Dijk , Ruth Montgomery , Guy Wolf , Smita Krishnaswamy