中文
相关论文

相关论文: The Phase Transition Phenomenon of Shuffled Regres…

200 篇论文

With extensive variational simulations, dissipative quantum phase transitions in the sub-Ohmic spin-boson model are numerically studied in a dense limit of environmental modes. By employing a generalized trial wave function composed of…

统计力学 · 物理学 2023-09-06 Yulong Shen , Nengji Zhou

We consider the problem of inference in a linear regression model in which the relative ordering of the input features and output labels is not known. Such datasets naturally arise from experiments in which the samples are shuffled or…

机器学习 · 统计学 2018-04-04 Abubakar Abid , James Zou

Mean field-like approximations (including naive mean field, Bethe and Kikuchi and more general Cluster Variational Methods) are known to stabilize ordered phases at temperatures higher than the thermodynamical transition. For example, in…

无序系统与神经网络 · 物理学 2015-06-22 A. Lage-Castellanos , R. Mulet , F. Ricci-Tersenghi

A model of noise reduction (NR) for signal processing is introduced. Each noise source puts a symmetric constraint on the space of the signal vector within a tolerable overlap. When the number of noise sources increases, sequences of…

无序系统与神经网络 · 物理学 2007-05-23 J. van Mourik , K. Y. Michael Wong , D. Bolle'

Due to the massive number of devices in the M2M communication era, new challenges have been brought to the existing random-access (RA) mechanism, such as severe preamble collisions and resource block (RB) wastes. To address these problems,…

信息论 · 计算机科学 2019-10-09 Zhaoji Zhang , Ying Li , Lei Liu , Huimei Han

We consider a variant of regression problem, where the correspondence between input and output data is not available. Such shuffled data is commonly observed in many real world problems. Taking flow cytometry as an example, the measuring…

机器学习 · 计算机科学 2021-02-12 Yujia Xie , Yixiu Mao , Simiao Zuo , Hongteng Xu , Xiaojing Ye , Tuo Zhao , Hongyuan Zha

Compressed sensing posits that, within limits, one can undersample a sparse signal and yet reconstruct it accurately. Knowing the precise limits to such undersampling is important both for theory and practice. We present a formula that…

信息论 · 计算机科学 2013-01-09 David Donoho , Iain Johnstone , Andrea Montanari

We study the posterior distribution of the Bayesian multiple change-point regression problem when the number and the locations of the change-points are unknown. While it is relatively easy to apply the general theory to obtain the…

统计理论 · 数学 2008-08-21 Heng Lian

We consider the statistical inference problem of recovering an unknown perfect matching, hidden in a weighted random graph, by exploiting the information arising from the use of two different distributions for the weights on the edges…

无序系统与神经网络 · 物理学 2020-08-10 Guilhem Semerjian , Gabriele Sicuro , Lenka Zdeborová

In many real-world problems, recovering sparse signals from underdetermined linear systems remains a fundamental challenge. Although $\ell_1$ norm minimization is widely used, it suffers from estimation bias that prevents it from reaching…

信息论 · 计算机科学 2026-04-16 Keisuke Morita , Federico Ricci-Tersenghi , Masayuki Ohzeki

We consider the behaviour of open quantum systems in dependence on the coupling to one decay channel by introducing the coupling parameter $\alpha$ being proportional to the average degree of overlapping. Under critical conditions, a…

量子物理 · 物理学 2009-10-31 C. Jung , M. Mueller , I. Rotter

We study a spectral initialization method that serves a key role in recent work on estimating signals in nonconvex settings. Previous analysis of this method focuses on the phase retrieval problem and provides only performance bounds. In…

信息论 · 计算机科学 2019-07-23 Yue M. Lu , Gen Li

Linear regression with shuffled labels and with a noisy latent design matrix arises in many correspondence recovery problems. We propose a total least-squares approach to the problem of estimating the underlying true permutation and provide…

统计理论 · 数学 2022-09-05 Qian Wang , Daniel Sussman

A quenched second order phase transition is modeled by an effective $\Phi^4$-theory with a time-dependent Hamiltonian $\hat{H} (t)$, whose symmetry is broken spontaneously in time. The quantum field evolves out of equilibrium…

高能物理 - 唯象学 · 物理学 2009-11-07 Sang Pyo Kim , Supratim Sengupta , F. C. Khanna

We consider the Blume-Capel model with the quantum tunneling between the excited states. We find a magnetically ordered phase transition induced by quantum fluctuation in a model. The model has no phase transition in the corresponding…

统计力学 · 物理学 2007-05-23 Norikazu Todoroki , Seiji Miyashita

We consider tensor factorizations using a generative model and a Bayesian approach. We compute rigorously the mutual information, the Minimal Mean Squared Error (MMSE), and unveil information-theoretic phase transitions. In addition, we…

统计理论 · 数学 2020-01-22 Thibault Lesieur , Léo Miolane , Marc Lelarge , Florent Krzakala , Lenka Zdeborová

Recently, there has been significant interest in linear regression in the situation where predictors and responses are not observed in matching pairs corresponding to the same statistical unit as a consequence of separate data collection…

统计方法学 · 统计学 2019-10-04 Martin Slawski , Guoqing Diao , Emanuel Ben-David

In phase retrieval, the goal is to recover a complex signal from the magnitude of its linear measurements. While many well-known algorithms guarantee deterministic recovery of the unknown signal using i.i.d. random measurement matrices,…

信息论 · 计算机科学 2017-03-24 Boshra Rajaei , Sylvain Gigan , Florent Krzakala , Laurent Daudet

We review connections between phase transitions in high-dimensional combinatorial geometry and phase transitions occurring in modern high-dimensional data analysis and signal processing. In data analysis, such transitions arise as abrupt…

统计理论 · 数学 2015-05-13 David L. Donoho , Jared Tanner

We establish the convergence rates and asymptotic distributions of the common break change-point estimators, obtained by least squares and maximum likelihood in panel data models and compare their asymptotic variances. Our model assumptions…

统计理论 · 数学 2017-08-22 Monika Bhattacharjee , Moulinath Banerjee , George Michailidis