English
Related papers

Related papers: We Need to Talk About Random Splits

200 papers

The Adaptive Multilevel Splitting algorithm is a very powerful and versatile iterative method to estimate the probability of rare events, based on an interacting particle systems. In an other article, in a so-called idealized setting, the…

Probability · Mathematics 2019-10-21 Charles-Edouard Bréhier , Ludovic Goudenège , Loic Tudela

Selective classification enhances the reliability of predictive models by allowing them to abstain from making uncertain predictions. In this work, we revisit the design of optimal selection functions through the lens of the Neyman--Pearson…

Machine Learning · Computer Science 2026-03-04 Alvin Heng , Harold Soh

We investigate a new sampling scheme aimed at improving the performance of particle filters whenever (a) there is a significant mismatch between the assumed model dynamics and the actual system, or (b) the posterior probability tends to…

Computation · Statistics 2019-03-20 Ömer Deniz Akyıldız , Joaquín Míguez

Despite achieving excellent performance on benchmarks, deep neural networks often underperform in real-world deployment due to sensitivity to minor, often imperceptible shifts in input data, known as distributional shifts. These shifts are…

Machine Learning · Computer Science 2025-09-25 Birk Torpmann-Hagen , Pål Halvorsen , Michael A. Riegler , Dag Johansen

We introduce a set of resampling-based methods for quantifying uncertainty and statistical precision of evaluation metrics in multilingual and/or multitask NLP benchmarks. We show how experimental variation in performance scores arises from…

Computation and Language · Computer Science 2025-12-19 Jonne Sälevä , Duygu Ataman , Constantine Lignos

Over the past decades, researchers and ML practitioners have come up with better and better ways to build, understand and improve the quality of ML models, but mostly under the key assumption that the training data is distributed…

Machine Learning · Computer Science 2019-10-14 Yeounoh Chung , Peter J. Haas , Eli Upfal , Tim Kraska

Combating bias in NLP requires bias measurement. Bias measurement is almost always achieved by using lexicons of seed terms, i.e. sets of words specifying stereotypes or dimensions of interest. This reproducibility study focuses on the…

Computation and Language · Computer Science 2022-06-07 Jille van der Togt , Lea Tiyavorabun , Matteo Rosati , Giulio Starace

This paper is an attempt to set a justification for making use of some dicrepancy indexes, starting from the classical Maximum Likelihood definition, and adapting the corresponding basic principle of inference to situations where…

Statistics Theory · Mathematics 2021-02-24 Michel Broniatowski

In reliable decision-making systems based on machine learning, models have to be robust to distributional shifts or provide the uncertainty of their predictions. In node-level problems of graph learning, distributional shifts can be…

Machine Learning · Computer Science 2023-11-02 Gleb Bazhenov , Denis Kuznedelev , Andrey Malinin , Artem Babenko , Liudmila Prokhorenkova

A growing body of research has demonstrated the inability of NLP models to generalize compositionally and has tried to alleviate it through specialized architectures, training schemes, and data augmentation, among other approaches. In this…

Computation and Language · Computer Science 2022-11-03 Shivanshu Gupta , Sameer Singh , Matt Gardner

This article emphasizes that NLP as a science seeks to make inferences about the performance effects that result from applying one method (compared to another method) in the processing of natural language. Yet NLP research in practice…

Computation and Language · Computer Science 2022-09-15 Sandra Wankmüller

Thousands of person-years have been invested in searches for New Physics (NP), the majority of them motivated by theoretical considerations. Yet, no evidence of beyond the Standard Model (BSM) physics has been found. This suggests that…

High Energy Physics - Experiment · Physics 2024-10-22 Shikma Bressler , Inbar Savoray , Yuval Zurgil

Logical reasoning is needed in a wide range of NLP tasks. Can a BERT model be trained end-to-end to solve logical reasoning problems presented in natural language? We attempt to answer this question in a confined problem space where there…

Computation and Language · Computer Science 2022-05-26 Honghua Zhang , Liunian Harold Li , Tao Meng , Kai-Wei Chang , Guy Van den Broeck

Sampling is often a necessary evil to reduce the processing and storage costs of distributed tracing. In this work, we describe a scalable and adaptive sampling approach that can preserve events of interest better than the widely used…

Data Structures and Algorithms · Computer Science 2021-07-19 Otmar Ertl

The most popular approach for analyzing survival data is the Cox regression model. The Cox model may, however, be misspecified, and its proportionality assumption may not always be fulfilled. An alternative approach for survival prediction…

Machine Learning · Statistics 2018-05-17 Marvin N. Wright , Theresa Dankowski , Andreas Ziegler

Statistical inference is often simplified by sample-splitting. This simplification comes at the cost of the introduction of randomness not native to the data. We propose a simple procedure for sequentially aggregating statistics constructed…

Econometrics · Economics 2024-11-18 David M. Ritzwoller , Joseph P. Romano

Mixup is a highly successful technique to improve generalization of neural networks by augmenting the training data with combinations of random pairs. Selective mixup is a family of methods that apply mixup to specific pairs, e.g. only…

Machine Learning · Computer Science 2023-06-06 Damien Teney , Jindong Wang , Ehsan Abbasnejad

Two-sample inference for the difference of population means typically relies upon a Central Limit Theorem approximation. When data are drawn from a Negative Binomial distribution, previous work of Shilane et al. (2010) showed that a Normal…

Methodology · Statistics 2012-03-06 David Shilane , Derek Bean

Methods for split conformal prediction leverage calibration samples to transform any prediction rule into a set-prediction rule that complies with a target coverage probability. Existing methods provide remarkably strong performance…

Machine Learning · Statistics 2025-10-15 Santiago Mazuelas

Statistical models that include random effects are commonly used to analyze longitudinal and correlated data, often with strong and parametric assumptions about the random effects distribution. There is marked disagreement in the literature…

Methodology · Statistics 2012-01-11 Charles E. McCulloch , John M. Neuhaus