paper-with-me

Papers

Semi-Supervised Sparse Gaussian Classification: Provable Benefits of Unlabeled Data

2024-09-05 · Eyar Azar, Boaz Nadler

The premise of semi-supervised learning (SSL) is that combining labeled and unlabeled data yields significantly more accurate models. Despite empirical successes, the theoretical understanding of SSL is still far from complete. In this work, we study SSL for high dimensional sparse Gaussian classification. To construct an accurate classifier a key task is feature selection, detecting the few variables that separate the two classes. % For this SSL setting, we analyze information theoretic lower bounds for accurate feature selection as well as computational lower bounds, assuming the low-degree likelihood hardness conjecture. % Our key contribution is the identification of a regime in the problem parameters (dimension, sparsity, number of labeled and unlabeled samples) where SSL is guaranteed to be advantageous for classification. Specifically, there is a regime where it is possible to construct in polynomial time an accurate SSL classifier. However, % any computationally efficient supervised or unsupervised learning schemes, that separately use only the labeled or unlabeled data would fail. Our work highlights the provable benefits of combining labeled and unlabeled data for {classification and} feature selection in high dimensions. We present simulations that complement our theoretical analysis.

📄 PDF Abstract BibTeX arXiv:2409.03335

Code (0)

등록된 구현이 없습니다.

Tasks

feature selection

Methods 이 논문이 사용한 방법론

Feature Selection Feature selection, also known as variable selection, attribute selection or variable subset selection, is the process of selecting a subset of relevant features (variables,…

Similar Papers 제목 키워드 기반

Semi-unsupervised Learning of Human Activity using Deep Generative Models

2018-10-29 · Matthew Willetts, Aiden Doherty, Stephen Roberts, Chris Holmes

We introduce 'semi-unsupervised learning', a problem regime related to transfer learning and zero-shot learning where, in the training data, some classes are sparsely labelled and others entirely unlabelled. Models able …

ClassificationGeneral ClassificationTime SeriesTime Series Analysis+2

Outlier-Robust Tensor PCA

2017-07-01 · CVPR 2017 7 · Pan Zhou, Jiashi Feng

Low-rank tensor analysis is important for various real applications in computer vision. However, existing methods focus on recovering a low-rank tensor contaminated by Gaussian or gross sparse noise and hence cannot effe…

ClusteringOutlier Detection

Semi-unsupervised Learning for Time Series Classification

2022-07-07 · Padraig Davidson, Michael Steininger, André Huhn, Anna Krause 외

Time series are ubiquitous and therefore inherently hard to analyze and ultimately to label or cluster. With the rise of the Internet of Things (IoT) and its smart devices, data is collected in large amounts any given se…

ClassificationTime SeriesTime Series AnalysisTime Series Classification

Semi-supervised dictionary learning with graph regularization and active points

2020-09-13 · Khanh-Hung Tran, Fred-Maurice Ngole-Mboula, Jean-Luc Starck, Vincent Prost

Supervised Dictionary Learning has gained much interest in the recent decade and has shown significant performance improvements in image classification. However, in general, supervised learning needs a large number of la…

Dictionary LearningGeneral Classificationimage-classificationImage Classification

Differentially Private Regression and Classification with Sparse Gaussian Processes

2019-09-19 · Michael Thomas Smith, Mauricio A. Alvarez, Neil D. Lawrence

A continuing challenge for machine learning is providing methods to perform computation on data while ensuring the data remains private. In this paper we build on the provable privacy guarantees of differential privacy w…

ClassificationGaussian ProcessesGeneral Classificationregression