English
Related papers

Related papers: Lossless Analog Compression

200 papers

Early works on medical image compression date to the 1980's with the impetus on deployment of teleradiology systems for high-resolution digital X-ray detectors. Commercially deployed systems during the period could compress 4,096 x 4,096…

Computer Vision and Pattern Recognition · Computer Science 2018-05-21 Aupendu Kar , Sri Phani Krishna Karri , Nirmalya Ghosh , Ramanathan Sethuraman , Debdoot Sheet

We study the problem of lossless feature selection for a $d$-dimensional feature vector $X=(X^{(1)},\dots ,X^{(d)})$ and label $Y$ for binary classification as well as nonparametric regression. For an index set $S\subset \{1,\dots ,d\}$,…

Statistics Theory · Mathematics 2024-11-26 László Györfi , Tamás Linder , Harro Walk

Artificial Neural-Network-based (ANN-based) lossy compressors have recently obtained striking results on several sources. Their success may be ascribed to an ability to identify the structure of low-dimensional manifolds in high-dimensional…

Information Theory · Computer Science 2022-09-13 Sourbh Bhadane , Aaron B. Wagner , Johannes Ballé

We consider the problem of reconstructing an unknown bounded function $u$ defined on a domain $X\subset \mathbb{R}^d$ from noiseless or noisy samples of $u$ at $n$ points $(x^i)_{i=1,\dots,n}$. We measure the reconstruction error in a norm…

Numerical Analysis · Mathematics 2016-08-02 Albert Cohen , Giovanni Migliorati

The impressive growth of data throughput in optical microscopy has triggered a widespread use of supervised learning (SL) models running on compressed image datasets for efficient automated analysis. However, since lossy image compression…

Let $(X,\mathcal{B},m,\tau)$ be a dynamical system with $\ds (X,\mathcal{B},m)$ a probability space and $\ds \tau$ an invertible, measure preserving transformation. The present paper deals with the almost everywhere convergence in…

Classical Analysis and ODEs · Mathematics 2011-04-19 Karin Reinhold , Anna Savvopoulou , Christopher Wedrychowicz

In this paper we obtain the rates of convergence of the algorithms given in [13] and [14] for an automatic computation of the centered Hausdorff and packing measures of a totally disconnected self-similar set. We evaluate these rates…

Dynamical Systems · Mathematics 2017-04-26 Marta Llorente , M. Eugenia Mera , Manuel Moran

Recent findings by Jahn, T. Ullrich, Voigtlaender [10] relate non-linear sampling numbers for the square norm to quantities involving trigonometric best $m-$term approximation errors in the uniform norm. Here we establish new results for…

Numerical Analysis · Mathematics 2024-07-24 Moritz Moeller , Serhii Stasyuk , Tino Ullrich

A new Lossy Causal Temporal Convolutional Neural Network Autoencoder for anomaly detection is proposed in this work. Our framework uses a rate-distortion loss and an entropy bottleneck to learn a compressed latent representation for the…

Machine Learning · Computer Science 2022-12-06 Christopher P. Ley , Jorge F. Silva

Traditional sampling theories consider the problem of reconstructing an unknown signal $x$ from a series of samples. A prevalent assumption which often guarantees recovery from the given measurements is that $x$ lies in a known subspace.…

Cellular Automata and Lattice Gases · Physics 2009-03-30 Yonina C. Eldar , Moshe Mishali

Compressed sensing allows for the recovery of sparse signals from few measurements, whose number is proportional to the sparsity of the unknown signal, up to logarithmic factors. The classical theory typically considers either random linear…

Functional Analysis · Mathematics 2025-04-02 Giovanni S. Alberti , Alessandro Felisi , Matteo Santacesaria , S. Ivan Trapasso

We consider the problem of recovering a real-valued $n$-dimensional signal from $m$ phaseless, linear measurements and analyze the amplitude-based non-smooth least squares objective. We establish local convergence of subgradient descent…

Machine Learning · Computer Science 2021-08-31 Paul Hand , Oscar Leong , Vladislav Voroninski

As in standard linear regression, in truncated linear regression, we are given access to observations $(A_i, y_i)_i$ whose dependent variable equals $y_i= A_i^{\rm T} \cdot x^* + \eta_i$, where $x^*$ is some fixed unknown vector of interest…

Machine Learning · Computer Science 2020-07-30 Constantinos Daskalakis , Dhruv Rohatgi , Manolis Zampetakis

The class of complex random vectors whose covariance matrix is linearly parameterized by a basis of Hermitian Toeplitz (HT) matrices is considered, and the maximum compression ratios that preserve all second-order information are derived…

Statistics Theory · Mathematics 2016-11-15 Daniel Romero , Roberto Lopez-Valcarce , Geert Leus

In many linear inverse problems, we want to estimate an unknown vector belonging to a high-dimensional (or infinite-dimensional) space from few linear measurements. To overcome the ill-posed nature of such problems, we use a low-dimension…

Information Theory · Computer Science 2017-07-18 Yann Traonmilin , Gilles Puy , Rémi Gribonval , Mike Davies

In the context of linear regression, we construct a data-driven convex loss function with respect to which empirical risk minimisation yields optimal asymptotic variance in the downstream estimation of the regression coefficients. At the…

Statistics Theory · Mathematics 2025-05-29 Oliver Y. Feng , Yu-Chun Kao , Min Xu , Richard J. Samworth

In compressed sensing the goal is to recover a signal from as few as possible noisy, linear measurements. The general assumption is that the signal has only a few non-zero entries. The recovery can be performed by multiple different…

Information Theory · Computer Science 2020-10-07 Hendrik Bernd Petersen , Bubacarr Bah , Peter Jung

We describe an image compression method, consisting of a nonlinear analysis transformation, a uniform quantizer, and a nonlinear synthesis transformation. The transforms are constructed in three successive stages of convolutional linear…

Computer Vision and Pattern Recognition · Computer Science 2020-07-28 Johannes Ballé , Valero Laparra , Eero P. Simoncelli

We give lower bounds for the problem of stable sparse recovery from /adaptive/ linear measurements. In this problem, one would like to estimate a vector $x \in \R^n$ from $m$ linear measurements $A_1x,..., A_mx$. One may choose each vector…

Data Structures and Algorithms · Computer Science 2012-10-23 Eric Price , David P. Woodruff

This paper considers the use of the anisotropic total variation seminorm to recover a two dimensional vector $x\in \mathbb{C}^{N\times N}$ from its partial Fourier coefficients, sampled along Cartesian lines. We prove that if $(x_{k,j} -…

Information Theory · Computer Science 2016-02-09 Clarice Poon