中文
相关论文

相关论文: Optimality of Approximate Message Passing Algorith…

200 篇论文

We consider the task of estimating a low-rank matrix from non-linear and noisy observations. We prove a strong universality result showing that Bayes-optimal performances are characterized by an equivalent Gaussian model with an effective…

机器学习 · 统计学 2024-03-08 Pierre Mergny , Justin Ko , Florent Krzakala , Lenka Zdeborová

Practical systems often suffer from hardware impairments that already appear during signal generation. Despite the limiting effect of such input-noise impairments on signal processing systems, they are routinely ignored in the literature.…

信号处理 · 电气工程与系统科学 2021-10-04 Ramina Ghods , Charles Jeon , Arian Maleki , Christoph Studer

Maximum a posteriori (MAP) inference in discrete-valued Markov random fields is a fundamental problem in machine learning that involves identifying the most likely configuration of random variables given a distribution. Due to the…

机器学习 · 计算机科学 2020-07-03 Jonathan N. Lee , Aldo Pacchiano , Peter Bartlett , Michael I. Jordan

In matrix recovery from random linear measurements, one is interested in recovering an unknown $M$-by-$N$ matrix $X_0$ from $n<MN$ measurements $y_i=Tr(A_i^T X_0)$ where each $A_i$ is an $M$-by-$N$ measurement matrix with i.i.d random…

信息论 · 计算机科学 2021-09-21 Elad Romanov , Matan Gavish

It is well known that the class of rotation invariant algorithms are suboptimal even for learning sparse linear problems when the number of examples is below the "dimension" of the problem. This class includes any gradient descent trained…

机器学习 · 统计学 2024-03-06 Manfred K. Warmuth , Wojciech Kotłowski , Matt Jones , Ehsan Amid

Iterative thresholding algorithms are well-suited for high-dimensional problems in sparse recovery and compressive sensing. The performance of this class of algorithms depends heavily on the tuning of certain threshold parameters. In…

信息论 · 计算机科学 2013-11-04 Ali Mousavi , Arian Maleki , Richard G. Baraniuk

Recent work has generalized several results concerning the well-understood spiked Wigner matrix model of a low-rank signal matrix corrupted by additive i.i.d. Gaussian noise to the inhomogeneous case, where the noise has a variance profile.…

统计理论 · 数学 2025-10-10 Debsurya De , Dmitriy Kunisky

This paper deals with the trace regression model where $n$ entries or linear combinations of entries of an unknown $m_1\times m_2$ matrix $A_0$ corrupted by noise are observed. We propose a new nuclear norm penalized estimator of $A_0$ and…

统计理论 · 数学 2016-03-24 Vladimir Koltchinskii , Alexandre B. Tsybakov , Karim Lounici

The matrix completion problem consists in reconstructing a matrix from a sample of entries, possibly observed with noise. A popular class of estimator, known as nuclear norm penalized estimators, are based on minimizing the sum of a data…

统计理论 · 数学 2015-04-21 Jean Lafond

We consider a problem of significant practical importance, namely, the reconstruction of a low-rank data matrix from a small subset of its entries. This problem appears in many areas such as collaborative filtering, computer vision and…

机器学习 · 计算机科学 2009-11-04 Raghunandan H. Keshavan , Andrea Montanari , Sewoong Oh

Both theoretical analysis and empirical evidence confirm that the approximate message passing (AMP) algorithm can be interpreted as recursively solving a signal denoising problem: at each AMP iteration, one observes a Gaussian noise…

信息论 · 计算机科学 2015-06-22 Chunli Guo , Mike E. Davies

Bayesian methods for low-rank matrix completion with noise have been shown to be very efficient computationally. While the behaviour of penalized minimization methods is well understood both from the theoretical and computational points of…

统计理论 · 数学 2015-04-08 The Tien Mai , Pierre Alquier

Factorization of matrices where the rank of the two factors diverges linearly with their sizes has many applications in diverse areas such as unsupervised representation learning, dictionary learning or sparse coding. We consider a setting…

无序系统与神经网络 · 物理学 2022-08-11 Antoine Maillard , Florent Krzakala , Marc Mézard , Lenka Zdeborová

We develop a data-driven optimal shrinkage algorithm for matrix denoising in the presence of high-dimensional noise with a separable covariance structure; that is, the noise is colored and dependent across samples. The algorithm, coined…

应用统计 · 统计学 2024-05-14 Pei-Chun Su , Hau-Tieng Wu

Motivated by applications in single-cell biology and metagenomics, we investigate the problem of matrix reordering based on a noisy disordered monotone Toeplitz matrix model. We establish the fundamental statistical limit for this problem…

统计理论 · 数学 2023-08-15 T. Tony Cai , Rong Ma

In this paper, we provide a novel algorithm for solving planning and learning problems of Markov decision processes. The proposed algorithm follows a policy iteration-type update by using a rank-one approximation of the transition…

We propose a data-driven algorithm for the maximum a posteriori (MAP) estimation of stochastic processes from noisy observations. The primary statistical properties of the sought signal is specified by the penalty function (i.e., negative…

机器学习 · 计算机科学 2018-02-14 Ha Q. Nguyen , Emrah Bostan , Michael Unser

In this paper, we propose a new algorithm for recovery of low-rank matrices from compressed linear measurements. The underlying idea of this algorithm is to closely approximate the rank function with a smooth function of singular values,…

信息论 · 计算机科学 2016-11-18 Mohammadreza Malek-Mohammadi , Massoud Babaie-Zadeh , Mikael Skoglund

Phase noise (PN) is a major disturbance in MIMO systems, where the contribution of different oscillators at the transmitter and the receiver side may degrade the overall performance and offset the gains offered by MIMO techniques. This is…

信息论 · 计算机科学 2024-05-14 Alberto Tarable , Francisco J. Escribano

This paper examines a general class of noisy matrix completion tasks where the goal is to estimate a matrix from observations obtained at a subset of its entries, each of which is subject to random noise or corruption. Our specific focus is…

机器学习 · 统计学 2016-11-18 Akshay Soni , Swayambhoo Jain , Jarvis Haupt , Stefano Gonella