English
Related papers

Related papers: Subspace Learning from Extremely Compressed Measur…

200 papers

Large-scale eigenvalue problems arise in various fields of science and engineering and demand computationally efficient solutions. In this study, we investigate the subspace approximation for parametric linear eigenvalue problems, aiming to…

Given a full rank matrix $X$ with more columns than rows, consider the task of estimating the pseudo inverse $X^+$ based on the pseudo inverse of a sampled subset of columns (of size at least the number of rows). We show that this is…

Machine Learning · Computer Science 2018-06-07 Michał Dereziński , Manfred K. Warmuth

Word embedding is a useful approach to capture co-occurrence structures in large text corpora. However, in addition to the text data itself, we often have additional covariates associated with individual corpus documents---e.g. the…

Computation and Language · Computer Science 2018-07-10 Kevin Tian , Teng Zhang , James Zou

In this paper, we address two challenging problems in unsupervised subspace learning: 1) how to automatically identify the feature dimension of the learned subspace (i.e., automatic subspace learning), and 2) how to learn the underlying…

Computer Vision and Pattern Recognition · Computer Science 2017-05-17 Xi Peng , Jiwen Lu , Zhang Yi , Rui Yan

Compressive Learning is an emerging topic that combines signal acquisition via compressive sensing and machine learning to perform inference tasks directly on a small number of measurements. Many data modalities naturally have a…

Computer Vision and Pattern Recognition · Computer Science 2020-10-22 Dat Thanh Tran , Mehmet Yamac , Aysen Degerli , Moncef Gabbouj , Alexandros Iosifidis

We find that different Deep Neural Networks (DNNs) trained with the same dataset share a common principal subspace in latent spaces, no matter in which architectures (e.g., Convolutional Neural Networks (CNNs), Multi-Layer Preceptors (MLPs)…

Machine Learning · Computer Science 2021-10-07 Haoran Liu , Haoyi Xiong , Yaqing Wang , Haozhe An , Dongrui Wu , Dejing Dou

This paper focuses on the estimation of the sample covariance matrix from low-dimensional random projections of data known as compressive measurements. In particular, we present an unbiased estimator to extract the covariance structure from…

Machine Learning · Statistics 2017-05-01 Farhad Pourkamali-Anaraki

We introduce a learning-based algorithm to obtain a measurement matrix for compressive sensing related recovery problems. The focus lies on matrices with a constant modulus constraint which typically represent a network of analog phase…

Signal Processing · Electrical Eng. & Systems 2021-10-15 Michael Koller , Wolfgang Utschick

How many samples are sufficient to guarantee that the eigenvectors and eigenvalues of the sample covariance matrix are close to those of the actual covariance matrix? For a wide family of distributions, including distributions with finite…

Machine Learning · Statistics 2017-02-20 Andreas Loukas

The goal of subspace learning is to find a $k$-dimensional subspace of $\mathbb{R}^d$, such that the expected squared distance between instance vectors and the subspace is as small as possible. In this paper we study subspace learning in a…

Machine Learning · Computer Science 2016-05-27 Alon Gonen , Dan Rosenbaum , Yonina Eldar , Shai Shalev-Shwartz

We consider the problem of subspace estimation in situations where the number of available snapshots and the observation dimension are comparable in magnitude. In this context, traditional subspace methods tend to fail because the…

Information Theory · Computer Science 2016-11-15 Pascal Vallet , Philippe Loubaton , Xavier Mestre

Approximate learning machines have become popular in the era of small devices, including quantised, factorised, hashed, or otherwise compressed predictors, and the quest to explain and guarantee good generalisation abilities for such…

Machine Learning · Computer Science 2022-03-16 Andrew J. Turner , Ata Kabán

Active subspaces can effectively reduce the dimension of high-dimensional parameter studies enabling otherwise infeasible experiments with expensive simulations. The key components of active subspace methods are the eigenvectors of a…

Numerical Analysis · Mathematics 2015-07-03 Paul Constantine , David Gleich

We present the self-encoder, a neural network trained to guess the identity of each data sample. Despite its simplicity, it learns a very useful representation of data, in a self-supervised way. Specifically, the self-encoder learns to…

Machine Learning · Computer Science 2023-06-27 Armand Boschin , Thomas Bonald , Marc Jeanmougin

Motivated by applications such as sparse PCA, in this paper we present provably-accurate one-pass algorithms for the sparse approximation of the top eigenvectors of extremely massive matrices based on a single compact linear sketch. The…

Information Theory · Computer Science 2026-05-06 Edem Boahen , Simone Brugiapaglia , Hung-Hsu Chou , Mark Iwen , Felix Krahmer

Minimizing cross-entropy over the softmax scores of a linear map composed with a high-capacity encoder is arguably the most popular choice for training neural networks on supervised learning tasks. However, recent works show that one can…

Machine Learning · Statistics 2023-03-03 Florian Graf , Christoph D. Hofer , Marc Niethammer , Roland Kwitt

The goal of compressed sensing is to estimate a vector from an underdetermined system of noisy linear measurements, by making use of prior knowledge on the structure of vectors in the relevant domain. For almost all results in this…

Machine Learning · Statistics 2017-03-10 Ashish Bora , Ajil Jalal , Eric Price , Alexandros G. Dimakis

Compressed sensing techniques enable efficient acquisition and recovery of sparse, high-dimensional data signals via low-dimensional projections. In this work, we propose Uncertainty Autoencoders, a learning framework for unsupervised…

Machine Learning · Statistics 2019-04-15 Aditya Grover , Stefano Ermon

We propose a method for the approximation of high- or even infinite-dimensional feature vectors, which play an important role in supervised learning. The goal is to reduce the size of the training data, resulting in lower storage…

Machine Learning · Statistics 2021-04-06 Patrick Gelß , Stefan Klus , Ingmar Schuster , Christof Schütte

We consider the general problem of matching a subspace to a signal in R^N that has been observed indirectly (compressed) through a random projection. We are interested in the case where the collection of K-dimensional subspaces is…

Information Theory · Computer Science 2014-07-22 William Mantzel , Justin Romberg