English
Related papers

Related papers: Noisy nonlinear information and entropy numbers

200 papers

We consider the problem of recovering a signal observed in Gaussian noise. If the set of signals is convex and compact, and can be specified beforehand, one can use classical linear estimators that achieve a risk within a constant factor of…

Statistics Theory · Mathematics 2017-06-05 Dmitry Ostrovsky , Zaid Harchaoui , Anatoli Juditsky , Arkadi Nemirovski

We study the worst case tractability of multivariate linear problems defined on separable Hilbert spaces. Information about a problem instance consists of noisy evaluations of arbitrary bounded linear functionals, where the noise is either…

Numerical Analysis · Mathematics 2023-03-30 Leszek Plaskota , Paweł Siedlecki

Some physical processes, including the intensity fluctuations of a chaotic laser, the detection of single photons, and the Brownian motion of a microscopic particle in a fluid are unpredictable, at least on long timescales. This…

Chaotic Dynamics · Physics 2015-08-10 Aaron M. Hagerstrom , Thomas E. Murphy , Rajarshi Roy

Reliability of machine learning evaluation -- the consistency of observed evaluation scores across replicated model training runs -- is affected by several sources of nondeterminism which can be regarded as measurement noise. Current…

Machine Learning · Computer Science 2023-10-10 Michael Hagmann , Philipp Meier , Stefan Riezler

Tensor decomposition is a powerful tool for extracting physically meaningful latent factors from multi-dimensional nonnegative data, and has been an increasing interest in a variety of fields such as image processing, machine learning, and…

Machine Learning · Computer Science 2024-12-03 Xiongjun Zhang , Michael K. Ng

Consider the $n$-dimensional vector $y=X\be+\e$, where $\be \in \R^p$ has only $k$ nonzero entries and $\e \in \R^n$ is a Gaussian noise. This can be viewed as a linear system with sparsity constraints, corrupted by noise. We find a…

Information Theory · Computer Science 2009-10-13 Kamiar Rahnama Rad

We study the information loss of a class of inference strategies that is solely based on time averaging. For an array of independent binary sensors (e.g., receptors, single electron transistors) measuring a weak random signal (e.g., ligand…

Statistical Mechanics · Physics 2016-10-25 David Hartich , Udo Seifert

This article presents near-optimal guarantees for accurate and robust image recovery from under-sampled noisy measurements using total variation minimization. In particular, we show that from O(slog(N)) nonadaptive linear measurements, an…

Computer Vision and Pattern Recognition · Computer Science 2015-03-20 Deanna Needell , Rachel Ward

In this paper, we study the phase retrieval problem in the situation where the vector to be recovered has an a priori structure that can encoded into a regularization term. This regularizer is intended to promote solutions conforming to…

Optimization and Control · Mathematics 2024-07-24 Jean-Jacques Godeme , Jalal Fadili

In inverse problems, one attempts to infer spatially variable functions from indirect measurements of a system. To practitioners of inverse problems, the concept of "information" is familiar when discussing key questions such as which parts…

Numerical Analysis · Mathematics 2025-02-12 Wolfgang Bangerth , Chris R. Johnson , Dennis K. Njeru , Bart van Bloemen Waanders

We study the problem of recovering an incomplete $m\times n$ matrix of rank $r$ with columns arriving online over time. This is known as the problem of life-long matrix completion, and is widely applied to recommendation system, computer…

Machine Learning · Computer Science 2016-12-04 Maria-Florina Balcan , Hongyang Zhang

In this work, conditional entropy is used to quantify the information loss induced by passing a continuous random variable through a memoryless nonlinear input-output system. We derive an expression for the information loss depending on the…

Information Theory · Computer Science 2012-02-03 Bernhard C. Geiger , Christian Feldbauer , Gernot Kubin

Label noise is a critical factor that degrades the generalization performance of deep neural networks, thus leading to severe issues in real-world problems. Existing studies have employed strategies based on either loss or uncertainty to…

Machine Learning · Computer Science 2020-08-17 Wonyoung Shin , Jung-Woo Ha , Shengzhe Li , Yongwoo Cho , Hoyean Song , Sunyoung Kwon

This article considers recovery of signals that are sparse or approximately sparse in terms of a (possibly) highly overcomplete and coherent tight frame from undersampled data corrupted with additive noise. We show that the properly…

Information Theory · Computer Science 2013-09-10 Junhong Lin , Song Li

Noisy labels can impair the performance of deep neural networks. To tackle this problem, in this paper, we propose a new method for filtering label noise. Unlike most existing methods relying on the posterior probability of a noisy…

Computer Vision and Pattern Recognition · Computer Science 2022-01-31 Pengxiang Wu , Songzhu Zheng , Mayank Goswami , Dimitris Metaxas , Chao Chen

In this short note, we consider the worst case noise robustness of any phase retrieval algorithm which aims to reconstruct all nonvanishing vectors $\mathbf{x} \in \mathbb{C}^d$ (up to a single global phase multiple) from the magnitudes of…

Numerical Analysis · Mathematics 2018-06-22 Mark A. Iwen , Sami Merhi , Michael Perlmutter

Inverse optimization refers to the inference of unknown parameters of an optimization problem based on knowledge of its optimal solutions. This paper considers inverse optimization in the setting where measurements of the optimal solutions…

Optimization and Control · Mathematics 2017-12-27 Anil Aswani , Zuo-Jun Max Shen , Auyon Siddiq

We consider the problem of recovering a high-dimensional structured signal from independent Gaussian linear measurements each of which is quantized to $b$ bits. Our interest is in linear approaches to signal recovery, where "linear" means…

Information Theory · Computer Science 2016-07-12 Martin Slawski , Ping Li

It is well-known that point sources with sufficient mutual distance can be reconstructed exactly from finitely many Fourier measurements by solving a convex optimization problem with Tikhonov-regularization (this property is sometimes…

Optimization and Control · Mathematics 2023-12-13 Martin Holler , Benedikt Wirth

A common approach in positive-unlabeled learning is to train a classification model between labeled and unlabeled data. This strategy is in fact known to give an optimal classifier under mild conditions; however, it results in biased…

Machine Learning · Statistics 2017-02-03 Shantanu Jain , Martha White , Predrag Radivojac