English
Related papers

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

200 papers

In machine learning, if the training data is an unbiased sample of an underlying distribution, then the learned classification function will make accurate predictions for new samples. However, if the training data is not an unbiased sample,…

Machine Learning · Computer Science 2019-01-15 Wouter M. Kouw , Marco Loog

The choice of making an intervention depends on its potential benefit or harm in comparison to alternatives. Estimating the likely outcome of alternatives from observational data is a challenging problem as all outcomes are never observed,…

Machine Learning · Statistics 2020-02-18 Yao Zhang , Alexis Bellot , Mihaela van der Schaar

We prove risk bounds for binary classification in high-dimensional settings when the sample size is allowed to be smaller than the dimensionality of the training set observations. In particular, we prove upper bounds for both 'compressive…

Statistics Theory · Mathematics 2017-09-29 Ata Kaban , Robert J. Durrant

Cross-validation techniques for risk estimation and model selection are widely used in statistics and machine learning. However, the understanding of the theoretical properties of learning via model selection with cross-validation risk…

Machine Learning · Statistics 2024-05-27 Diego Marcondes , Cláudia Peixoto

We study the problem of computing the tightest upper and lower bounds on the probability that the sum of $n$ dependent Bernoulli random variables exceeds an integer $k$. Under knowledge of all pairs of bivariate distributions denoted by a…

Optimization and Control · Mathematics 2019-10-16 Divya Padmanabhan , Karthik Natarajan

Constructing confidence intervals that are simultaneously valid across a class of estimates is central to tasks such as multiple mean estimation, generalization guarantees, and adaptive experimental design. We frame this as an ``error…

Machine Learning · Computer Science 2026-02-05 Sanath Kumar Krishnamurthy , Anna Lyubarskaja , Emma Brunskill , Susan Athey

One of the central problems in machine learning is domain adaptation. Unlike past theoretical work, we consider a new model for subpopulation shift in the input or representation space. In this work, we propose a provably effective…

Machine Learning · Computer Science 2021-07-21 Tianle Cai , Ruiqi Gao , Jason D. Lee , Qi Lei

Estimating the generalization performance is practically challenging on out-of-distribution (OOD) data without ground-truth labels. While previous methods emphasize the connection between distribution difference and OOD accuracy, we show…

Machine Learning · Computer Science 2023-10-24 Renchunzi Xie , Hongxin Wei , Lei Feng , Yuzhou Cao , Bo An

Predictive models that generalize well under distributional shift are often desirable and sometimes crucial to building robust and reliable machine learning applications. We focus on distributional shift that arises in causal inference from…

Machine Learning · Statistics 2018-02-27 Fredrik D. Johansson , Nathan Kallus , Uri Shalit , David Sontag

We present a simple framework for one-class classification and anomaly detection. The core idea is to learn a mapping to transform the unknown distribution of training (normal) data to a known target distribution. Crucially, the target…

Machine Learning · Computer Science 2023-07-11 Feng Xiao , Ruoyu Sun , Jicong Fan

In this paper, we propose a novel self-supervised transfer learning method called \underline{\textbf{D}}istribution \underline{\textbf{M}}atching (DM), which drives the representation distribution toward a predefined reference distribution…

Machine Learning · Statistics 2025-07-03 Yuling Jiao , Wensen Ma , Defeng Sun , Hansheng Wang , Yang Wang

The label shift problem refers to the supervised learning setting where the train and test label distributions do not match. Existing work addressing label shift usually assumes access to an \emph{unlabelled} test sample. This sample may be…

Machine Learning · Computer Science 2021-08-18 Jingzhao Zhang , Aditya Menon , Andreas Veit , Srinadh Bhojanapalli , Sanjiv Kumar , Suvrit Sra

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 consider the weakly supervised binary classification problem where the labels are randomly flipped with probability $1- {\alpha}$. Although there exist numerous algorithms for this problem, it remains theoretically unexplored how the…

Machine Learning · Computer Science 2019-07-16 Xinyang Yi , Zhaoran Wang , Zhuoran Yang , Constantine Caramanis , Han Liu

We consider models of Bayesian inference of signals with vectorial components of finite dimensionality. We show that, under a proper perturbation, these models are replica symmetric in the sense that the overlap matrix concentrates. The…

Information Theory · Computer Science 2020-01-27 Jean Barbier

When facing uncertainty, decision-makers want predictions they can trust. A machine learning provider can convey confidence to decision-makers by guaranteeing their predictions are distribution calibrated -- amongst the inputs that receive…

Machine Learning · Statistics 2021-07-14 Shengjia Zhao , Michael P. Kim , Roshni Sahoo , Tengyu Ma , Stefano Ermon

Distribution shifts are ubiquitous in real-world machine learning applications, posing a challenge to the generalization of models trained on one data distribution to another. We focus on scenarios where data distributions vary across…

Machine Learning · Statistics 2024-06-05 Steven Wilkins-Reeves , Xu Chen , Qi Ma , Christine Agarwal , Aude Hofleitner

Robustness to distribution shift has become a growing concern for text and image models as they transition from research subjects to deployment in the real world. However, high-quality benchmarks for distribution shift in tabular machine…

Machine Learning · Computer Science 2024-02-12 Josh Gardner , Zoran Popovic , Ludwig Schmidt

A probabilistic model is said to be calibrated if its predicted probabilities match the corresponding empirical frequencies. Calibration is important for uncertainty quantification and decision making in safety-critical applications. While…

Machine Learning · Computer Science 2020-07-01 Anusri Pampari , Stefano Ermon

The increased availability of massive data sets provides a unique opportunity to discover subtle patterns in their distributions, but also imposes overwhelming computational challenges. To fully utilize the information contained in big…

Statistics Theory · Mathematics 2018-04-12 Stanislav Volgushev , Shih-Kang Chao , Guang Cheng