English
Related papers

Related papers: An Upper Bound for the Distribution Overlap Index …

200 papers

We introduce a framework for proving lower bounds on computational problems over distributions against algorithms that can be implemented using access to a statistical query oracle. For such algorithms, access to the input distribution is…

Computational Complexity · Computer Science 2016-08-16 Vitaly Feldman , Elena Grigorescu , Lev Reyzin , Santosh Vempala , Ying Xiao

A standard approach in pattern classification is to estimate the distributions of the label classes, and then to apply the Bayes classifier to the estimates of the distributions in order to classify unlabeled examples. As one might expect,…

Machine Learning · Computer Science 2007-05-23 Nick Palmer , Paul W. Goldberg

As we deploy machine learning systems in the real world, a core challenge is to maintain a model that is performant even as the data shifts. Such shifts can take many forms: new classes may emerge that were absent during training, a problem…

Machine Learning · Computer Science 2026-05-20 Shravan Chaudhari , Yoav Wald , Suchi Saria

Recent studies give more attention to the anomaly detection (AD) methods that can leverage a handful of labeled anomalies along with abundant unlabeled data. These existing anomaly-informed AD methods rely on manually predefined score…

Machine Learning · Computer Science 2023-06-27 Minqi Jiang , Songqiao Han , Hailiang Huang

We establish nearly optimal upper and lower bounds for approximating decision tree splits in data streams. For regression with labels in the range $\{0,1,\ldots,M\}$, we give a one-pass algorithm using $\tilde{O}(M^2/\epsilon)$ space that…

Data Structures and Algorithms · Computer Science 2026-04-23 Hoang Ta , Hoa T. Vu

The softmax representation of probabilities for categorical variables plays a prominent role in modern machine learning with numerous applications in areas such as large scale classification, neural language modeling and recommendation…

Machine Learning · Statistics 2016-11-01 Michalis K. Titsias

Our main focus is on the generalization bound, which serves as an upper limit for the generalization error. Our analysis delves into regression and classification tasks separately to ensure a thorough examination. We assume the target…

Machine Learning · Statistics 2024-07-30 Wen-Liang Hwang

Influence overlap is a universal phenomenon in influence spreading for social networks. In this paper, we argue that the redundant influence generated by influence overlap cause negative effect for maximizing spreading influence. Firstly,…

Social and Information Networks · Computer Science 2019-03-04 Ning Wang , Zi-Yi Wang , Jian-Guo Liu , Jing-Ti Han

The basic underlying assumption of machine learning (ML) models is that the training and test data are sampled from the same distribution. However, in daily practice, this assumption is often broken, i.e. the distribution of the test data…

Computation and Language · Computer Science 2026-01-16 Adriana Valentina Costache , Silviu Florin Gheorghe , Eduard Gabriel Poesina , Paul Irofti , Radu Tudor Ionescu

Class imbalance poses a significant challenge in classification tasks, where traditional approaches often lead to biased models and unreliable predictions. Undersampling and oversampling techniques have been commonly employed to address…

Machine Learning · Computer Science 2025-10-22 Matt Clifford , Jonathan Erskine , Alexander Hepburn , Raúl Santos-Rodríguez , Dario Garcia-Garcia

We study the open-set label shift problem, where the test data may include a novel class absent from training. This setting is challenging because both the class proportions and the distribution of the novel class are not identifiable…

Methodology · Statistics 2025-09-19 Siyan Liu , Yukun Liu , Qinglong Tian , Pengfei Li , Jing Qin

The identification of causal effects in observational studies typically relies on two standard assumptions: unconfoundedness and overlap. However, both assumptions are often questionable in practice: unconfoundedness is inherently…

Methodology · Statistics 2025-09-17 Han Cui , Xinran Li

Successful unsupervised domain adaptation is guaranteed only under strong assumptions such as covariate shift and overlap between input domains. The latter is often violated in high-dimensional applications like image classification which,…

Machine Learning · Computer Science 2024-06-13 Adam Breitholtz , Anton Matsson , Fredrik D. Johansson

Point estimation of class prevalences in the presence of data set shift has been a popular research topic for more than two decades. Less attention has been paid to the construction of confidence and prediction intervals for estimates of…

Machine Learning · Statistics 2019-07-23 Dirk Tasche

Class distribution plays an important role in learning deep classifiers. When the proportion of each class in the test set differs from the training set, the performance of classification nets usually degrades. Such a label distribution…

Image and Video Processing · Electrical Eng. & Systems 2022-07-12 Wenao Ma , Cheng Chen , Shuang Zheng , Jing Qin , Huimao Zhang , Qi Dou

The multi-index model is a simple yet powerful high-dimensional regression model which circumvents the curse of dimensionality assuming $ \mathbb{E} [ Y | X ] = g(A^\top X) $ for some unknown index space $A$ and link function $g$. In this…

Statistics Theory · Mathematics 2020-06-04 Timo Klock , Alessandro Lanteri , Stefano Vigogna

We propose a universal classifier for binary Neyman-Pearson classification where null distribution is known while only a training sequence is available for the alternative distribution. The proposed classifier interpolates between…

Information Theory · Computer Science 2022-06-24 Parham Boroumand , Albert Guillén i Fàbregas

Universal Domain Adaptation (UNDA) aims to handle both domain-shift and category-shift between two datasets, where the main challenge is to transfer knowledge while rejecting unknown classes which are absent in the labeled source data but…

Computer Vision and Pattern Recognition · Computer Science 2021-08-25 Kuniaki Saito , Kate Saenko

Transfer learning enhances prediction accuracy on a target distribution by leveraging data from a source distribution, demonstrating significant benefits in various applications. This paper introduces a novel dissimilarity measure that…

Machine Learning · Statistics 2024-12-12 Mitsuhiro Fujikawa , Yohei Akimoto , Jun Sakuma , Kazuto Fukuchi

The concentration of a distribution toward a lower bound is a conceptually simple property that closely relates to concepts of rarity and poverty, but that lacks a global descriptive statistic. We term this property 'shift' and define it as…

Methodology · Statistics 2025-06-16 Kenneth J. Locey , Brian D. Stein