中文
相关论文

相关论文: Living near the edge: A lower-bound on the phase t…

200 篇论文

Total variation denoising (TVD) is a classical method for denoising and curve fitting, yet an explicit pointwise description of its fitted values has only recently been established in the mean regression setting by arXiv:2410.03041v4. This…

统计理论 · 数学 2026-05-05 Deep Ghoshal , Sabyasachi Chatterjee

Compressed Sensing suggests that the required number of samples for reconstructing a signal can be greatly reduced if it is sparse in a known discrete basis, yet many real-world signals are sparse in a continuous dictionary. One example is…

信息论 · 计算机科学 2015-07-24 Yuanxin Li , Yuejie Chi

The total variation (TV)-seminorm is considered for piecewise polynomial, globally discontinuous (DG) and continuous (CG) finite element functions on simplicial meshes. A novel, discrete variant (DTV) based on a nodal quadrature formula is…

We present an analysis of total-variation (TV) on non-Euclidean parameterized surfaces, a natural representation of the shapes used in 3D graphics. Our work explains recent experimental findings in shape spectral TV [Fumero et al., 2020]…

计算几何 · 计算机科学 2024-02-05 Jonathan Brokman , Martin Burger , Guy Gilboa

In many areas of imaging science, it is difficult to measure the phase of linear measurements. As such, one often wishes to reconstruct a signal from intensity measurements, that is, perform phase retrieval. In several applications the…

信息论 · 计算机科学 2015-06-16 Afonso S. Bandeira , Dustin G. Mixon

We consider the initial situation where a dataset has been over-partitioned into $k$ clusters and seek a domain independent way to merge those initial clusters. We identify the total variation distance (TVD) as suitable for this goal. By…

机器学习 · 计算机科学 2019-12-10 Christian Reiser , Jörg Schlötterer , Michael Granitzer

The total variation distance is a core statistical distance between probability measures that satisfies the metric axioms, with value always falling in $[0,1]$. This distance plays a fundamental role in machine learning and signal…

机器学习 · 计算机科学 2018-07-02 Frank Nielsen , Ke Sun

In this paper we investigate the problem of recovering the source term in an elliptic system from a measurement of the state on a part of the boundary. For the particular interest in reconstructing probably discontinuous sources, we use the…

数值分析 · 数学 2020-01-08 Michael Hinze , Tran Nhan Tam Quyen

Two aspects of neural networks that have been extensively studied in the recent literature are their function approximation properties and their training by gradient descent methods. The approximation problem seeks accurate approximations…

机器学习 · 计算机科学 2022-09-20 R. Gentile , G. Welper

In this paper, we propose an adaptive finite difference scheme in order to numerically solve total variation type problems for image processing tasks. The automatic generation of the grid relies on indicators derived from a local estimation…

数值分析 · 数学 2024-10-18 Thomas Jacumin , Andreas Langer

In distributed optimization problems, a technique called gradient coding, which involves replicating data points, has been used to mitigate the effect of straggling machines. Recent work has studied approximate gradient coding, which…

机器学习 · 统计学 2021-08-09 Margalit Glasgow , Mary Wootters

We propose and analyze a method for semi-supervised learning from partially-labeled network-structured data. Our approach is based on a graph signal recovery interpretation under a clustering hypothesis that labels of data points belonging…

机器学习 · 计算机科学 2020-01-08 Alexander Jung , Alfred O. Hero , Alexandru Mara , Saeed Jahromi , Ayelet Heimowitz , Yonina C. Eldar

With the proliferation of generative AI and the increasing volume of generative data (also called as synthetic data), assessing the fidelity of generative data has become a critical concern. In this paper, we propose a discriminative…

机器学习 · 统计学 2024-05-27 Lan Tao , Shirong Xu , Chi-Hua Wang , Namjoon Suh , Guang Cheng

Tight bounds for several symmetric divergence measures are derived in terms of the total variation distance. It is shown that each of these bounds is attained by a pair of 2 or 3-element probability distributions. An application of these…

信息论 · 计算机科学 2016-11-17 Igal Sason

Phase retrieval (PR) is a popular research topic in signal processing and machine learning. However, its performance degrades significantly when the measurements are corrupted by noise or outliers. To address this limitation, we propose a…

最优化与控制 · 数学 2025-05-30 Jun Fan , Ailing Yan , Xianchao Xiu , Wanquan Liu

Evaluating the statistical dimension is a common tool to determine the asymptotic phase transition in compressed sensing problems with Gaussian ensemble. Unfortunately, the exact evaluation of the statistical dimension is very difficult and…

信息论 · 计算机科学 2019-06-06 Sajad Daei , Farzan Haddadi , Arash Amini , Martin Lotz

We study unique recovery of cosparse signals from limited-angle tomographic measurements of two- and three-dimensional domains. Admissible signals belong to the union of subspaces defined by all cosupports of maximal cardinality $\ell$ with…

数值分析 · 数学 2013-11-05 Andreea Deniţiu , Stefania Petra , Claudius Schnörr , Christoph Schnörr

We study the problem of recovering piecewise-polynomial periodic functions from their low-frequency information. This means that we only have access to possibly corrupted versions of the Fourier samples of the ground truth up to a maximum…

最优化与控制 · 数学 2022-02-11 Thomas Debarre , Quentin Denoyelle , Julien Fageot

The convergence of GD and SGD when training mildly parameterized neural networks starting from random initialization is studied. For a broad range of models and loss functions, including the most commonly used square loss and cross entropy…

机器学习 · 计算机科学 2023-05-30 Mingze Wang , Chao Ma

Discrete gradient methods are well-known methods of Geometric Numerical Integration, which preserve the dissipation of gradient systems. The preservation of the dissipation of a system is an important feature in numerous image processing…

数值分析 · 数学 2016-03-25 V Grimm , R I McLachlan , D McLaren , G R W Quispel , C-B Schönlieb