English
Related papers

Related papers: An Automatic Finite-Sample Robustness Metric: When…

200 papers

In many applications, different populations are compared using data that are sampled in a biased manner. Under sampling biases, standard methods that estimate the difference between the population means yield unreliable inferences. Here we…

Statistics Theory · Mathematics 2019-11-12 Dave Zachariah , Petre Stoica

Influence estimation methods promise to explain and debug machine learning by estimating the impact of individual samples on the final model. Yet, existing methods collapse under training randomness: the same example may appear critical in…

Machine Learning · Computer Science 2026-04-06 Subhodip Panda , Dhruv Tarsadiya , Shashwat Sourav , Prathosh A. P , Sai Praneeth Karimireddy

We give a method for proactively identifying small, plausible shifts in distribution which lead to large differences in model performance. These shifts are defined via parametric changes in the causal mechanisms of observed variables, where…

Machine Learning · Computer Science 2023-01-18 Nikolaj Thams , Michael Oberst , David Sontag

Effective data selection is critical for efficient training of modern Large Language Models (LLMs). This paper introduces Influence Distillation, a novel, mathematically-justified framework for data selection that employs second-order…

Computation and Language · Computer Science 2025-05-27 Mahdi Nikdan , Vincent Cohen-Addad , Dan Alistarh , Vahab Mirrokni

Small influential data subsets can dramatically impact model conclusions, with a few data points overturning key findings. While recent work identifies these most influential sets, there is no formal way to tell when maximum influence is…

Machine Learning · Statistics 2026-03-06 Lucas Darius Konrad , Nikolas Kuschnig

Quantifying the influence of infinitesimal changes in training data on model performance is crucial for understanding and improving machine learning models. In this work, we reformulate this problem as a weighted empirical risk minimization…

Machine Learning · Computer Science 2025-04-11 Omri Lev , Ashia C. Wilson

Despite the risk of misspecification they are tied to, parametric models continue to be used in statistical practice because they are accessible to all. In particular, efficient estimation procedures in parametric models are simple to…

Statistics Theory · Mathematics 2016-09-01 Marco Carone , Alexander R. Luedtke , Mark J. van der Laan

Causal inference from observational data provides strong evidence for the best action in decision-making without performing expensive randomized trials. The effect of an action is usually not identifiable under unobserved confounding, even…

Machine Learning · Computer Science 2026-02-02 Md Musfiqur Rahman , Ziwei Jiang , Hilaf Hasson , Murat Kocaoglu

The Central Limit Theorem provides a foundation for inferential statistics and hypothesis testing. It describes how standardized statistics behave under repeated sampling from large populations. However, if the size of the sample (n)…

Methodology · Statistics 2026-05-19 Mike Crowhurst

In the time of Big Data, training complex models on large-scale data sets is challenging, making it appealing to reduce data volume for saving computation resources by subsampling. Most previous works in subsampling are weighted methods…

Machine Learning · Computer Science 2021-04-14 Zifeng Wang , Hong Zhu , Zhenhua Dong , Xiuqiang He , Shao-Lun Huang

We study the out-of-sample properties of robust empirical optimization problems with smooth $\phi$-divergence penalties and smooth concave objective functions, and develop a theory for data-driven calibration of the non-negative "robustness…

Machine Learning · Statistics 2020-05-20 Jun-Ya Gotoh , Michael Jong Kim , Andrew E. B. Lim

Influence functions estimate the effect of removing a training point on a model without the need to retrain. They are based on a first-order Taylor approximation that is guaranteed to be accurate for sufficiently small changes to the model,…

Machine Learning · Computer Science 2019-11-22 Pang Wei Koh , Kai-Siang Ang , Hubert H. K. Teo , Percy Liang

Understanding the influence of a training instance on a neural network model leads to improving interpretability. However, it is difficult and inefficient to evaluate the influence, which shows how a model's prediction would be changed if a…

Machine Learning · Computer Science 2021-11-22 Sosuke Kobayashi , Sho Yokoi , Jun Suzuki , Kentaro Inui

The Influence Function (IF) is a widely used technique for assessing the impact of individual training samples on model predictions. However, existing IF methods often fail to provide reliable influence estimates in deep neural networks,…

Machine Learning · Computer Science 2025-12-02 Xichen Ye , Yifan Wu , Weizhong Zhang , Cheng Jin , Yifan Chen

Fine-tuning large language models (LLMs) on chain-of-thought (CoT) data shows that a small amount of high-quality data can outperform massive datasets. Yet, what constitutes "quality" remains ill-defined. Existing reasoning methods rely on…

Machine Learning · Computer Science 2025-12-02 Prateek Humane , Paolo Cudrano , Daniel Z. Kaplan , Matteo Matteucci , Supriyo Chakraborty , Irina Rish

We present a novel inference approach that we call Sample Out-of-Sample (or SOS) inference. The approach can be used widely, ranging from semi-supervised learning to stress testing, and it is fundamental in the application of data-driven…

Statistics Theory · Mathematics 2021-03-22 Jose Blanchet , Yang Kang

Data subsampling has become widely recognized as a tool to overcome computational and economic bottlenecks in analyzing massive datasets. We contribute to the development of adaptive design for estimation of finite population…

Methodology · Statistics 2024-07-08 Henrik Imberg , Xiaomi Yang , Carol Flannagan , Jonas Bärgman

Empirical causal claims depend on many analyst decisions, from selecting covariates to choosing estimators. Existing robustness tools summarize how results vary across these choices, but, to the best of our knowledge, do not answer:…

Methodology · Statistics 2026-05-05 Hoang Dang , Luan Pham , Minh Nguyen

Importance sampling is a well developed method in statistics. Given a random variable $X$, the problem of estimating its expected value $\mu$ is addressed. The standard approach is to use the sample mean as an estimator $\bar x$. In…

Applications · Statistics 2014-05-09 Georg Hofmann

Annotated datasets are an essential ingredient to train, evaluate, compare and productionalize supervised machine learning models. It is therefore imperative that annotations are of high quality. For their creation, good quality management…

Machine Learning · Computer Science 2024-05-30 Jan-Christoph Klie , Juan Haladjian , Marc Kirchner , Rahul Nair