English
Related papers

Related papers: Algorithmic Stability for Adaptive Data Analysis

200 papers

In statistical learning, a dataset is often partitioned into two parts: the training set and the holdout (i.e., testing) set. For instance, the training set is used to learn a predictor, and then the holdout set is used for estimating the…

Machine Learning · Computer Science 2019-11-05 Jun Zhao

In many open environment applications, data are collected in the form of a stream, which exhibits an evolving distribution over time. How to design algorithms to track these evolving data distributions with provable guarantees, particularly…

Machine Learning · Computer Science 2024-11-06 Chao Xu , Xijia Tang , Guoqing Liu , Yuhua Qian , Chenping Hou

As the use of machine learning in high impact domains becomes widespread, the importance of evaluating safety has increased. An important aspect of this is evaluating how robust a model is to changes in setting or population, which…

Machine Learning · Computer Science 2021-03-16 Adarsh Subbaswamy , Roy Adams , Suchi Saria

Algorithmic stability is a central notion in learning theory that quantifies the sensitivity of an algorithm to small changes in the training data. If a learning algorithm satisfies certain stability properties, this leads to many important…

Machine Learning · Statistics 2025-04-01 Yuetian Luo , Rina Foygel Barber

Equivalence testing, a fundamental problem in the field of distribution testing, seeks to infer if two unknown distributions on $[n]$ are the same or far apart in the total variation distance. Conditional sampling has emerged as a powerful…

Data Structures and Algorithms · Computer Science 2024-03-08 Diptarka Chakraborty , Sourav Chakraborty , Gunjan Kumar , Kuldeep S. Meel

Informatics and technological advancements have triggered generation of huge volume of data with varied complexity in its management and analysis. Big Data analytics is the practice of revealing hidden aspects of such data and making…

Databases · Computer Science 2018-03-30 Bikram Karmakar , Indranil Mukhopadhyay

This paper studies the sample complexity of searching over multiple populations. We consider a large number of populations, each corresponding to either distribution P0 or P1. The goal of the search problem studied here is to find one…

Information Theory · Computer Science 2016-11-17 Matthew L. Malloy , Gongguo Tang , Robert D. Nowak

In this work, we revisit the problem of uniformity testing of discrete probability distributions. A fundamental problem in distribution testing, testing uniformity over a known domain has been addressed over a significant line of works, and…

Data Structures and Algorithms · Computer Science 2017-08-17 Tuğkan Batu , Clément L. Canonne

We present the first adaptive strategy for active learning in the setting of classification with smooth decision boundary. The problem of adaptivity (to unknown distributional parameters) has remained opened since the seminal work of Castro…

Machine Learning · Statistics 2017-11-28 Andrea Locatelli , Alexandra Carpentier , Samory Kpotufe

Uniform stability is a notion of algorithmic stability that bounds the worst case change in the model output by the algorithm when a single data point in the dataset is replaced. An influential work of Hardt et al. (2016) provides strong…

Machine Learning · Computer Science 2020-06-15 Raef Bassily , Vitaly Feldman , Cristóbal Guzmán , Kunal Talwar

The problem of handling adaptivity in data analysis, intentional or not, permeates a variety of fields, including test-set overfitting in ML challenges and the accumulation of invalid scientific discoveries. We propose a mechanism for…

Machine Learning · Computer Science 2019-04-03 Blake Woodworth , Vitaly Feldman , Saharon Rosset , Nathan Srebro

Prediction models often fail if train and test data do not stem from the same distribution. Out-of-distribution (OOD) generalization to unseen, perturbed test data is a desirable but difficult-to-achieve property for prediction models and…

Methodology · Statistics 2022-05-25 Lucas Kook , Beate Sick , Peter Bühlmann

Uncertainty estimation aims to evaluate the confidence of a trained deep neural network. However, existing uncertainty estimation approaches rely on low-dimensional distributional assumptions and thus suffer from the high dimensionality of…

Machine Learning · Computer Science 2023-10-26 Tsai Hor Chan , Kin Wai Lau , Jiajun Shen , Guosheng Yin , Lequan Yu

Modern data workflows are inherently adaptive, repeatedly querying the same dataset to refine and validate sequential decisions, but such adaptivity can lead to overfitting and invalid statistical inference. Adaptive Data Analysis (ADA)…

Machine Learning · Computer Science 2026-02-10 Joon Suk Huh

Uniform stability of a learning algorithm is a classical notion of algorithmic stability introduced to derive high-probability bounds on the generalization error (Bousquet and Elisseeff, 2002). Specifically, for a loss function with range…

Machine Learning · Computer Science 2019-03-19 Vitaly Feldman , Jan Vondrak

A common goal in statistics and machine learning is to learn models that can perform well against distributional shifts, such as latent heterogeneous subpopulations, unknown covariate shifts, or unmodeled temporal effects. We develop and…

Machine Learning · Statistics 2020-07-21 John Duchi , Hongseok Namkoong

Stochastic optimization of the Area Under the Precision-Recall Curve (AUPRC) is a crucial problem for machine learning. Although various algorithms have been extensively studied for AUPRC optimization, the generalization is only guaranteed…

Machine Learning · Computer Science 2022-09-28 Peisong Wen , Qianqian Xu , Zhiyong Yang , Yuan He , Qingming Huang

We study statistical inference and distributionally robust solution methods for stochastic optimization problems, focusing on confidence intervals for optimal values and solutions that achieve exact coverage asymptotically. We develop a…

Machine Learning · Statistics 2018-07-03 John Duchi , Peter Glynn , Hongseok Namkoong

The goal of machine learning is to find models that minimize prediction error on data that has not yet been seen. Its operational paradigm assumes access to a dataset $S$ and articulates a scheme for evaluating how well a given model…

Machine Learning · Computer Science 2026-04-22 Maxim Raginsky , Benjamin Recht

Forecasting the evolution of complex systems is one of the grand challenges of modern data science. The fundamental difficulty lies in understanding the structure of the observed stochastic process. In this paper, we show that every…

Statistics Theory · Mathematics 2020-01-01 Xiucai Ding , Zhou Zhou