English
Related papers

Related papers: Gaussian and Non-Gaussian Universality of Data Aug…

200 papers

The Gaussian mechanism is an essential building block used in multitude of differentially private data analysis algorithms. In this paper we revisit the Gaussian mechanism and show that the original analysis has several important…

Machine Learning · Computer Science 2018-06-08 Borja Balle , Yu-Xiang Wang

The paper considers so-called adaptive estimations of regression, distribution density and spectral density of a Gaussian stationary sequence, asymptotically optimal in order at a growing number of observation on any regular subspace…

Probability · Mathematics 2007-05-23 Eugene Ostrovsky , Leonid Sirota

Practitioners in diverse fields such as healthcare, economics and education are eager to apply machine learning to improve decision making. The cost and impracticality of performing experiments and a recent monumental increase in electronic…

Machine Learning · Computer Science 2023-08-01 Fredrik D. Johansson , Uri Shalit , Nathan Kallus , David Sontag

We present \textit{universal} estimators for the statistical mean, variance, and scale (in particular, the interquartile range) under pure differential privacy. These estimators are universal in the sense that they work on an arbitrary,…

Cryptography and Security · Computer Science 2023-04-04 Wei Dong , Ke Yi

A growing body of work shows that models exploit annotation artifacts to achieve state-of-the-art performance on standard crowdsourced benchmarks---datasets collected from crowdworkers to create an evaluation task---while still failing on…

Computation and Language · Computer Science 2020-10-13 William Huang , Haokun Liu , Samuel R. Bowman

Lossy data transformations by definition lose information. Yet, in modern machine learning, methods like data pruning and lossy data augmentation can help improve generalization performance. We study this paradox using a solvable model of…

Statistical Mechanics · Physics 2025-09-19 Alex Nguyen , David J. Schwab , Vudtiwat Ngampruetikorn

A major effort in modern high-dimensional statistics has been devoted to the analysis of linear predictors trained on nonlinear feature embeddings via empirical risk minimization (ERM). Gaussian equivalence theory (GET) has emerged as a…

Statistics Theory · Mathematics 2025-12-04 Garrett G. Wen , Hong Hu , Yue M. Lu , Zhou Fan , Theodor Misiakiewicz

Data augmentation plays a pivotal role in enhancing and diversifying training data. Nonetheless, consistently improving model performance in varied learning scenarios, especially those with inherent data biases, remains challenging. To…

Machine Learning · Computer Science 2024-06-04 Xiaoling Zhou , Wei Ye , Zhemg Lee , Rui Xie , Shikun Zhang

High dimensional data analysis is known to be as a challenging problem. In this article, we give a theoretical analysis of high dimensional classification of Gaussian data which relies on a geometrical analysis of the error measure. It…

Statistics Theory · Mathematics 2008-07-10 Robin Girard

This work investigates the impact of data augmentation on confidence calibration and uncertainty estimation in Named Entity Recognition (NER) tasks. For the future advance of NER in safety-critical fields like healthcare and finance, it is…

Computation and Language · Computer Science 2024-10-28 Wataru Hashimoto , Hidetaka Kamigaito , Taro Watanabe

Neural networks have proven successful at learning from complex data distributions by acting as universal function approximators. However, they are often overconfident in their predictions, which leads to inaccurate and miscalibrated…

Machine Learning · Computer Science 2021-02-23 Jeffrey Willette , Juho Lee , Sung Ju Hwang

Data augmentation is a major component of many machine learning methods with state-of-the-art performance. Common augmentation strategies work by drawing random samples from a space of transformations. Unfortunately, such sampling…

Machine Learning · Computer Science 2020-11-06 Calvin Luo , Hossein Mobahi , Samy Bengio

We propose a novel, succinct, and effective approach for distribution prediction to quantify uncertainty in machine learning. It incorporates adaptively flexible distribution prediction of $\mathbb{P}(\mathbf{y}|\mathbf{X}=x)$ in regression…

Machine Learning · Computer Science 2023-06-21 Xing Yan , Yonghua Su , Wenxuan Ma

Non-Bayesian social learning theory provides a framework for distributed inference of a group of agents interacting over a social network by sequentially communicating and updating beliefs about the unknown state of the world through…

Methodology · Statistics 2019-10-25 James Z. Hare , Cesar Uribe , Lance Kaplan , Ali Jadbabaie

We analyze gradient descent with randomly weighted data points in a linear regression model, under a generic weighting distribution. This includes various forms of stochastic gradient descent, importance sampling, but also extends to…

Machine Learning · Statistics 2025-12-12 Gabriel Clara , Yazan Mash'al

The quantification of uncertainties of computer simulations due to input parameter uncertainties is paramount to assess a model's credibility. For computationally expensive simulations, this is often feasible only via surrogate models that…

Methodology · Statistics 2021-08-30 Sascha Ranftl , Wolfgang von der Linden

I present here a generalization of the maximum likelihood method and the $\chi^2$ method to the cases in which the data are {\it not} assumed to be Gaussian distributed. The method, based on the multivariate Edgeworth expansion, can find…

Astrophysics · Physics 2007-05-23 Luca Amendola

The success of deep learning depends heavily on the availability of large datasets, but in robotic manipulation there are many learning problems for which such datasets do not exist. Collecting these datasets is time-consuming and…

Robotics · Computer Science 2022-07-21 Peter Mitrano , Dmitry Berenson

Data augmentation is a promising technique for unsupervised anomaly detection in industrial applications, where the availability of positive samples is often limited due to factors such as commercial competition and sample collection…

Computer Vision and Pattern Recognition · Computer Science 2023-04-25 Lingrui Zhang , Shuheng Zhang , Guoyang Xie , Jiaqi Liu , Hua Yan , Jinbao Wang , Feng Zheng , Yaochu Jin

Dynamic data selection aims to accelerate training with lossless performance. However, reducing training data inherently limits data diversity, potentially hindering generalization. While data augmentation is widely used to enhance…

Machine Learning · Computer Science 2025-05-13 Suorong Yang , Peng Ye , Furao Shen , Dongzhan Zhou