English
Related papers

Related papers: More General Queries and Less Generalization Error…

200 papers

We study the problem of estimating a set of $d$ linear queries with respect to some unknown distribution $\mathbf{p}$ over a domain $\mathcal{J}=[J]$ based on a sensitive data set of $n$ individuals under the constraint of local…

Machine Learning · Computer Science 2018-10-08 Raef Bassily

We provide universality results that quantify how data augmentation affects the variance and limiting distribution of estimates through simple surrogates, and analyze several specific models in detail. The results confirm some observations…

Machine Learning · Computer Science 2025-12-03 Kevin Han Huang , Peter Orbanz , Morgane Austern

The modeling of probability distributions, specifically generative modeling and density estimation, has become an immensely popular subject in recent years by virtue of its outstanding performance on sophisticated data such as images and…

Machine Learning · Statistics 2023-01-02 Hongkang Yang

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

In distributional or average-case analysis, the goal is to design an algorithm with good-on-average performance with respect to a specific probability distribution. Distributional analysis can be useful for the study of general-purpose…

Data Structures and Algorithms · Computer Science 2020-07-28 Tim Roughgarden

Generalization error bounds are essential to understanding machine learning algorithms. This paper presents novel expected generalization error upper bounds based on the average joint distribution between the output hypothesis and each…

Information Theory · Computer Science 2022-02-25 Gholamali Aminian , Yuheng Bu , Gregory Wornell , Miguel Rodrigues

Though data augmentation has become a standard component of deep neural network training, the underlying mechanism behind the effectiveness of these techniques remains poorly understood. In practice, augmentation policies are often chosen…

Machine Learning · Computer Science 2020-06-08 Raphael Gontijo-Lopes , Sylvia J. Smullin , Ekin D. Cubuk , Ethan Dyer

Intuitively, unfamiliarity should lead to lack of confidence. In reality, current algorithms often make highly confident yet wrong predictions when faced with relevant but unfamiliar examples. A classifier we trained to recognize gender is…

Computer Vision and Pattern Recognition · Computer Science 2020-09-09 Zhizhong Li , Derek Hoiem

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

This paper tackles the challenge of detecting unreliable behavior in regression algorithms, which may arise from intrinsic variability (e.g., aleatoric uncertainty) or modeling errors (e.g., model uncertainty). First, we formally introduce…

Machine Learning · Computer Science 2024-06-12 Andres Altieri , Marco Romanelli , Georg Pichler , Florence Alberge , Pablo Piantanida

We study adaptive approximation algorithms for general multivariate linear problems where the sets of input functions are non-convex cones. While it is known that adaptive algorithms perform essentially no better than non-adaptive…

Numerical Analysis · Mathematics 2019-03-27 Yuhan Ding , Fred J. Hickernell , Peter Kritzer , Simon Mak

We consider the problem of finding an edge in a hidden undirected graph $G = (V, E)$ with $n$ vertices, in a model where we only allowed queries that ask whether or not a subset of vertices contains an edge. We study the non-adaptive model…

Data Structures and Algorithms · Computer Science 2022-07-07 Ron Kupfer , Noam Nisan

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

Time-series anomaly detection deals with the problem of detecting anomalous timesteps by learning normality from the sequence of observations. However, the concept of normality evolves over time, leading to a "new normal problem", where the…

Machine Learning · Computer Science 2024-01-23 Dongmin Kim , Sunghyun Park , Jaegul Choo

The problem of sequential anomaly detection and identification is considered, where multiple data sources are simultaneously monitored and the goal is to identify in real time those, if any, that exhibit ``anomalous" statistical behavior.…

Statistics Theory · Mathematics 2024-12-09 Aristomenis Tsopelakos , Georgios Fellouris

Machine learning algorithms have achieved remarkable success across various disciplines, use cases and applications, under the prevailing assumption that training and test samples are drawn from the same distribution. Consequently, these…

Machine Learning · Computer Science 2024-11-07 Zehao Xiao , Cees G. M. Snoek

The Huge Object model is a distribution testing model in which we are given access to independent samples from an unknown distribution over the set of strings $\{0,1\}^n$, but are only allowed to query a few bits from the samples. We…

Data Structures and Algorithms · Computer Science 2024-09-18 Tomer Adar , Eldar Fischer , Amit Levi

Invariant approaches have been remarkably successful in tackling the problem of domain generalization, where the objective is to perform inference on data distributions different from those used in training. In our work, we investigate…

Computer Vision and Pattern Recognition · Computer Science 2021-03-31 Abhimanyu Dubey , Vignesh Ramanathan , Alex Pentland , Dhruv Mahajan

In this paper, we study the problem of estimating uniformly well the mean values of several distributions given a finite budget of samples. If the variance of the distributions were known, one could design an optimal sampling strategy by…

Machine Learning · Computer Science 2015-07-17 Alexandra Carpentier , Alessandro Lazaric , Mohammad Ghavamzadeh , Rémi Munos , Peter Auer , András Antos

This paper is motivated by an open problem around deep networks, namely, the apparent absence of over-fitting despite large over-parametrization which allows perfect fitting of the training data. In this paper, we analyze this phenomenon in…

Machine Learning · Computer Science 2019-08-28 Hrushikesh Mhaskar , Tomaso Poggio
‹ Prev 1 4 5 6 7 8 10 Next ›