English
Related papers

Related papers: A Statistical Analysis for Supervised Deep Learnin…

200 papers

Classifiers built with neural networks handle large-scale high dimensional data, such as facial images from computer vision, extremely well while traditional statistical methods often fail miserably. In this paper, we attempt to understand…

Machine Learning · Statistics 2020-02-04 Tianyang Hu , Zuofeng Shang , Guang Cheng

The goal of supervised representation learning is to construct effective data representations for prediction. Among all the characteristics of an ideal nonparametric representation of high-dimensional complex data, sufficiency, low…

Machine Learning · Computer Science 2022-09-02 Jian Huang , Yuling Jiao , Xu Liao , Jin Liu , Zhou Yu

We study the problem of overcoming exponential sample complexity in differential entropy estimation under Gaussian convolutions. Specifically, we consider the estimation of the differential entropy $h(X+Z)$ via $n$ independently and…

Information Theory · Computer Science 2023-05-12 Kristjan Greenewald , Brian Kingsbury , Yuancheng Yu

Recent works (e.g., (Li and Arora, 2020)) suggest that the use of popular normalization schemes (including Batch Normalization) in today's deep learning can move it far from a traditional optimization viewpoint, e.g., use of exponentially…

Machine Learning · Computer Science 2020-10-07 Zhiyuan Li , Kaifeng Lyu , Sanjeev Arora

The local intrinsic dimension (LID) of data is a fundamental quantity in signal processing and learning theory, but quantifying the LID of high-dimensional, complex data has been a historically challenging task. Recent works have discovered…

Machine Learning · Computer Science 2025-11-27 Eric Yeats , Aaron Jacobson , Darryl Hannan , Yiran Jia , Timothy Doster , Henry Kvinge , Scott Mahan

Unsupervised learning aims at the discovery of hidden structure that drives the observations in the real world. It is essential for success in modern machine learning. Latent variable models are versatile in unsupervised learning and have…

Machine Learning · Computer Science 2016-06-13 Furong Huang

We develop a new theoretical framework to analyze the generalization error of deep learning, and derive a new fast learning rate for two representative algorithms: empirical risk minimization and Bayesian deep learning. The series of…

Statistics Theory · Mathematics 2017-05-31 Taiji Suzuki

Disobeying the classical wisdom of statistical learning theory, modern deep neural networks generalize well even though they typically contain millions of parameters. Recently, it has been shown that the trajectories of iterative…

Machine Learning · Computer Science 2021-11-29 Tolga Birdal , Aaron Lou , Leonidas Guibas , Umut Şimşekli

In this work, we revisit the semi-supervised learning (SSL) problem from a new perspective of explicitly reducing empirical distribution mismatch between labeled and unlabeled samples. Benefited from this new perspective, we first propose a…

Computer Vision and Pattern Recognition · Computer Science 2022-03-15 Feiyu Wang , Qin Wang , Wen Li , Dong Xu , Luc Van Gool

This paper considers statistical inference for the explained variance $\beta^{\intercal}\Sigma \beta$ under the high-dimensional linear model $Y=X\beta+\epsilon$ in the semi-supervised setting, where $\beta$ is the regression vector and…

Methodology · Statistics 2020-12-01 T. Tony Cai , Zijian Guo

Classic supervised learning involves algorithms trained on $n$ labeled examples to produce a hypothesis $h \in \mathcal{H}$ aimed at performing well on unseen examples. Meta-learning extends this by training across $n$ tasks, with $m$…

Machine Learning · Statistics 2024-11-28 Yannay Alon , Steve Hanneke , Shay Moran , Uri Shalit

We study high-dimensional asymptotic performance limits of binary supervised classification problems where the class conditional densities are Gaussian with unknown means and covariances and the number of signal dimensions scales faster…

Machine Learning · Statistics 2016-11-17 Mohammad Hossein Rohban , Prakash Ishwar , Birant Orten , William C. Karl , Venkatesh Saligrama

We study approximation and statistical learning properties of deep ReLU networks under structural assumptions that mitigate the curse of dimensionality. We prove minimax-optimal uniform approximation rates for $s$-H\"older smooth functions…

Statistics Theory · Mathematics 2026-02-06 Thomas Nagler , Sophie Langer

The denoising diffusion probabilistic model (DDPM) has emerged as a mainstream generative model in generative AI. While sharp convergence guarantees have been established for the DDPM, the iteration complexity is, in general, proportional…

Machine Learning · Computer Science 2026-02-17 Zhihan Huang , Yuting Wei , Yuxin Chen

Many algorithms in machine learning and computational geometry require, as input, the intrinsic dimension of the manifold that supports the probability distribution of the data. This parameter is rarely known and therefore has to be…

Statistics Theory · Mathematics 2020-01-01 Jisu Kim , Alessandro Rinaldo , Larry Wasserman

The idea behind the \emph{unsupervised} learning of \emph{disentangled} representations is that real-world data is generated by a few explanatory factors of variation which can be recovered by unsupervised learning algorithms. In this…

Machine Learning · Computer Science 2020-10-29 Francesco Locatello , Stefan Bauer , Mario Lucic , Gunnar Rätsch , Sylvain Gelly , Bernhard Schölkopf , Olivier Bachem

Recent advances in deep learning from probability distributions successfully achieve classification or regression from distribution samples, thus invariant under permutation of the samples. The first contribution of the paper is to extend…

Machine Learning · Statistics 2020-10-20 Gwendoline De Bie , Herilalaina Rakotoarison , Gabriel Peyré , Michèle Sebag

This paper introduces a new notion of dimensionality of probabilistic models from an information-theoretic view point. We call it the "descriptive dimension"(Ddim). We show that Ddim coincides with the number of independent parameters for…

Machine Learning · Computer Science 2019-10-28 Kenji Yamanishi

While the manifold hypothesis is widely adopted in modern machine learning, complex data is often better modeled as stratified spaces -- unions of manifolds (strata) of varying dimensions. Stratified learning is challenging due to varying…

Machine Learning · Statistics 2026-04-14 Randy Martinez , Rong Tang , Lizhen Lin

In distributed statistical learning, $N$ samples are split across $m$ machines and a learner wishes to use minimal communication to learn as well as if the examples were on a single machine. This model has received substantial interest in…

Machine Learning · Computer Science 2019-03-19 Jayadev Acharya , Christopher De Sa , Dylan J. Foster , Karthik Sridharan