English
Related papers

Related papers: Optimality of Message-Passing Architectures for Sp…

200 papers

A localized method to distribute paths on random graphs is devised, aimed at finding the shortest paths between given source/destination pairs while avoiding path overlaps at nodes. We propose a method based on message-passing techniques to…

Disordered Systems and Neural Networks · Physics 2014-10-17 Caterina De Bacco , Silvio Franz , David Saad , Chi Ho Yeung

Graph signal processing (GSP) provides a powerful framework for analyzing signals arising in a variety of domains. In many applications of GSP, multiple network structures are available, each of which captures different aspects of the same…

Machine Learning · Statistics 2021-11-03 Michael Weylandt , George Michailidis , T. Mitchell Roddenberry

Graph neural networks (GNNs) have achieved champion in wide applications. Neural message passing is a typical key module for feature propagation by aggregating neighboring features. In this work, we propose a new message passing based on…

Machine Learning · Computer Science 2023-03-01 Xinliang Liu , Bingxin Zhou , Chutian Zhang , Yu Guang Wang

This study poses the feature correspondence problem as a hypergraph node labeling problem. Candidate feature matches and their subsets (usually of size larger than two) are considered to be the nodes and hyperedges of a hypergraph. A…

Computer Vision and Pattern Recognition · Computer Science 2011-07-14 Toufiq Parag , Vladimir Pavlovic , Ahmed Elgammal

Here we consider the problem of denoising features associated to complex data, modeled as signals on a graph, via a smoothness prior. This is motivated in part by settings such as single-cell RNA where the data is very high-dimensional, but…

Machine Learning · Computer Science 2023-12-12 Sam Leone , Xingzhi Sun , Michael Perlmutter , Smita Krishnaswamy

The goal of this thesis is to develop the optimisation and generalisation theoretic foundations of learning in artificial neural networks. On optimisation, a new theoretical framework is proposed for deriving architecture-dependent…

Neural and Evolutionary Computing · Computer Science 2022-10-20 Jeremy Bernstein

The increasing availability of graph-structured data motivates the task of optimising over functions defined on the node set of graphs. Traditional graph search algorithms can be applied in this case, but they may be sample-inefficient and…

Machine Learning · Computer Science 2023-10-31 Xingchen Wan , Pierre Osselin , Henry Kenlay , Binxin Ru , Michael A. Osborne , Xiaowen Dong

Within a Bayesian decision theoretic framework we investigate some asymptotic optimality properties of a large class of multiple testing rules. A parametric setup is considered, in which observations come from a normal scale mixture model…

Statistics Theory · Mathematics 2012-11-22 Małgorzata Bogdan , Arijit Chakrabarti , Florian Frommlet , Jayanta K. Ghosh

For the problem of binary linear classification and feature selection, we propose algorithmic approaches to classifier design based on the generalized approximate message passing (GAMP) algorithm, recently proposed in the context of…

Information Theory · Computer Science 2015-06-18 Justin Ziniel , Philip Schniter , Per Sederberg

We study sparse linear regression over a network of agents, modeled as an undirected graph and no server node. The estimation of the $s$-sparse parameter is formulated as a constrained LASSO problem wherein each agent owns a subset of the…

Machine Learning · Computer Science 2024-12-30 Marie Maros , Gesualdo Scutari , Ying Sun , Guang Cheng

In a semi-supervised learning scenario, (possibly noisy) partially observed labels are used as input to train a classifier, in order to assign labels to unclassified samples. In this paper, we study this classifier learning problem from a…

Machine Learning · Computer Science 2017-07-21 Gene Cheung , Weng-Tai Su , Yu Mao , Chia-Wen Lin

Many sparse linear discriminant analysis (LDA) methods have been proposed to overcome the major problems of the classic LDA in high-dimensional settings. However, the asymptotic optimality results are limited to the case that there are only…

Statistics Theory · Mathematics 2015-08-06 Ruiyan Luo , Xin Qi

We aim to learn a sparse and connected graph from sparse data, where the number of observations K can be substantially smaller than the signal dimension N for signals x in R^N, and the underlying distribution is unknown. In this severely…

Signal Processing · Electrical Eng. & Systems 2026-04-30 Bahar Oveisgharan , Gene Cheung , Andrew Eckford

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…

Machine Learning · Statistics 2024-03-06 Manfred K. Warmuth , Wojciech Kotłowski , Matt Jones , Ehsan Amid

Graphs are ubiquitous in modelling relational structures. Recent endeavours in machine learning for graph-structured data have led to many architectures and learning algorithms. However, the graph used by these algorithms is often…

Machine Learning · Statistics 2020-06-25 Soumyasundar Pal , Saber Malekmohammadi , Florence Regol , Yingxue Zhang , Yishi Xu , Mark Coates

Characterizing the distribution of high-dimensional statistical estimators is a challenging task, due to the breakdown of classical asymptotic theory in high dimension. This paper makes progress towards this by developing non-asymptotic…

Statistics Theory · Mathematics 2024-01-09 Gen Li , Yuting Wei

In this work, we formulate the fixed-length distribution matching as a Bayesian inference problem. Our proposed solution is inspired from the compressed sensing paradigm and the sparse superposition (SS) codes. First, we introduce sparsity…

Information Theory · Computer Science 2018-11-27 Mohamad Dia , Vahid Aref , Laurent Schmalen

We present a distributed (non-Bayesian) learning algorithm for the problem of parameter estimation with Gaussian noise. The algorithm is expressed as explicit updates on the parameters of the Gaussian beliefs (i.e. means and precision). We…

Optimization and Control · Mathematics 2016-12-08 Angelia Nedić , Alex Olshevsky , César A. Uribe

This work presents a two-stage neural architecture for learning and refining structural correspondences between graphs. First, we use localized node embeddings computed by a graph neural network to obtain an initial ranking of soft…

Machine Learning · Computer Science 2020-01-28 Matthias Fey , Jan E. Lenssen , Christopher Morris , Jonathan Masci , Nils M. Kriege

This paper addresses a distributed optimization problem in a communication network where nodes are active sporadically. Each active node applies some learning method to control its action to maximize the global utility function, which is…

Optimization and Control · Mathematics 2021-04-20 Wenjie Li , Mohamad Assaad , Shiqi Zheng