English
Related papers

Related papers: Refining the Adaptivity Notion in the Huge Object …

200 papers

We develop methods for forming prediction sets in an online setting where the data generating distribution is allowed to vary over time in an unknown fashion. Our framework builds on ideas from conformal inference to provide a general…

Methodology · Statistics 2021-12-10 Isaac Gibbs , Emmanuel Candès

Despite their recent success, deep neural networks continue to perform poorly when they encounter distribution shifts at test time. Many recently proposed approaches try to counter this by aligning the model to the new distribution prior to…

Computer Vision and Pattern Recognition · Computer Science 2022-09-26 Samarth Sinha , Peter Gehler , Francesco Locatello , Bernt Schiele

In the study of natural and artificial complex systems, responses that are not completely determined by the considered decision variables are commonly modelled probabilistically, resulting in response distributions varying across decision…

Methodology · Statistics 2021-10-07 Athénaïs Gautier , David Ginsbourger , Guillaume Pirot

Theoretical studies on transfer learning or domain adaptation have so far focused on situations with a known hypothesis class or model; however in practice, some amount of model selection is usually involved, often appearing under the…

Machine Learning · Statistics 2023-10-13 Steve Hanneke , Samory Kpotufe , Yasaman Mahdaviyeh

Adaptivity is an important feature of data analysis---typically the choice of questions asked about a dataset depends on previous interactions with the same dataset. However, generalization error is typically bounded in a non-adaptive…

Machine Learning · Computer Science 2015-11-11 Raef Bassily , Adam Smith , Thomas Steinke , Jonathan Ullman

We present a new adaptive algorithm for learning discrete distributions under distribution drift. In this setting, we observe a sequence of independent samples from a discrete distribution that is changing over time, and the goal is to…

Machine Learning · Computer Science 2024-03-11 Alessio Mazzetto

The framework of distribution testing is currently ubiquitous in the field of property testing. In this model, the input is a probability distribution accessible via independently drawn samples from an oracle. The testing task is to…

Data Structures and Algorithms · Computer Science 2022-09-22 Sourav Chakraborty , Eldar Fischer , Arijit Ghosh , Gopinath Mishra , Sayantan Sen

Most work on adaptive data analysis assumes that samples in the dataset are independent. When correlations are allowed, even the non-adaptive setting can become intractable, unless some structural constraints are imposed. To address this,…

Data Structures and Algorithms · Computer Science 2025-11-13 Emma Rapoport , Edith Cohen , Uri Stemmer

Most work on supervised learning research has focused on marginal predictions. In decision problems, joint predictive distributions are essential for good performance. Previous work has developed methods for assessing low-order predictive…

Machine Learning · Statistics 2022-03-01 Ian Osband , Zheng Wen , Seyed Mohammad Asghari , Vikranth Dwaracherla , Xiuyuan Lu , Benjamin Van Roy

We study distribution testing in the standard access model and the conditional access model when the memory available to the testing algorithm is bounded. In both scenarios, the samples appear in an online fashion and the goal is to test…

Data Structures and Algorithms · Computer Science 2023-09-08 Sampriti Roy , Yadu Vasudev

Domain adaptation aims to learn models on a supervised source domain that perform well on an unsupervised target. Prior work has examined domain adaptation in the context of stationary domain shifts, i.e. static data sets. However, with…

Computer Vision and Pattern Recognition · Computer Science 2018-08-03 Sindi Shkodrani , Michael Hofmann , Efstratios Gavves

Randomization testing is a fundamental method in statistics, enabling inferential tasks such as testing for (conditional) independence of random variables, constructing confidence intervals in semiparametric location models, and…

Methodology · Statistics 2023-03-21 Yash Nair , Lucas Janson

Recent years have witnessed the success of adaptive (or unified) approaches in estimating symmetric properties of discrete distributions, where one first obtains a distribution estimator independent of the target property, and then plugs…

Statistics Theory · Mathematics 2021-03-04 Yanjun Han

Online reinforcement learning and other adaptive sampling algorithms are increasingly used in digital intervention experiments to optimize treatment delivery for users over time. In this work, we focus on longitudinal user data collected by…

Machine Learning · Computer Science 2023-04-20 Kelly W. Zhang , Lucas Janson , Susan A. Murphy

The classification of random objects within metric spaces without a vector structure has attracted increasing attention. However, the complexity inherent in such non-Euclidean data often restricts existing models to handle only a limited…

Methodology · Statistics 2024-03-20 Shuaida He , Jiaqi Li , Xin Chen

The discrepancy between in-distribution (ID) and out-of-distribution (OOD) samples can lead to \textit{distributional vulnerability} in deep neural networks, which can subsequently lead to high-confidence predictions for OOD samples. This…

Machine Learning · Computer Science 2023-10-03 Zhilin Zhao , Longbing Cao , Kun-Yu Lin

Overfitting is the bane of data analysts, even when data are plentiful. Formal approaches to understanding this problem focus on statistical inference and generalization of individual analysis procedures. Yet the practice of data analysis…

Machine Learning · Computer Science 2015-09-28 Cynthia Dwork , Vitaly Feldman , Moritz Hardt , Toniann Pitassi , Omer Reingold , Aaron Roth

We propose self-adaptive training -- a unified training algorithm that dynamically calibrates and enhances training processes by model predictions without incurring an extra computational cost -- to advance both supervised and…

Machine Learning · Computer Science 2022-10-17 Lang Huang , Chao Zhang , Hongyang Zhang

Deep neural network training often involves stochastic optimization, meaning each run will produce a different model. This implies that hyperparameters of the training process, such as the random seed itself, can potentially have…

Machine Learning · Statistics 2025-04-17 Sinjini Banerjee , Tim Marrinan , Reilly Cannon , Tony Chiang , Anand D. Sarwate

While traditional Deep Learning (DL) optimization methods treat all training samples equally, Distributionally Robust Optimization (DRO) adaptively assigns importance weights to different samples. However, a significant gap exists between…