中文
相关论文

相关论文: Belief propagation for networks with loops: The ne…

200 篇论文

We study the problem of training and certifying adversarially robust quantized neural networks (QNNs). Quantization is a technique for making neural networks more efficient by running them using low-bit integer arithmetic and is therefore…

机器学习 · 计算机科学 2022-11-30 Mathias Lechner , Đorđe Žikelić , Krishnendu Chatterjee , Thomas A. Henzinger , Daniela Rus

Belief propagation (BP) is a classical algorithm that approximates the marginal distribution associated with a factor graph by passing messages between adjacent nodes in the graph. It gained popularity in the 1990's as a powerful decoding…

信息论 · 计算机科学 2022-07-12 S. Brandsen , Avijit Mandal , Henry D. Pfister

As traditional neural network consumes a significant amount of computing resources during back propagation, \citet{Sun2017mePropSB} propose a simple yet effective technique to alleviate this problem. In this technique, only a small subset…

机器学习 · 计算机科学 2017-09-27 Bingzhen Wei , Xu Sun , Xuancheng Ren , Jingjing Xu

The belief propagation (BP) algorithm is widely applied to perform approximate inference on arbitrary graphical models, in part due to its excellent empirical properties and performance. However, little is known theoretically about when…

人工智能 · 计算机科学 2012-06-26 Alexander T. Ihler

We consider inference (filtering) problems over probabilistic graphical models with aggregate data generated by a large population of individuals. We propose a new efficient belief propagation type algorithm over tree-structured graphs with…

机器学习 · 计算机科学 2020-10-06 Rahul Singh , Isabel Haasler , Qinsheng Zhang , Johan Karlsson , Yongxin Chen

Recently, researchers have demonstrated that loopy belief propagation - the use of Pearls polytree algorithm IN a Bayesian network WITH loops OF error- correcting codes.The most dramatic instance OF this IS the near Shannon - limit…

人工智能 · 计算机科学 2013-01-30 Kevin Murphy , Yair Weiss , Michael I. Jordan

Training neural networks with verifiable robustness guarantees is challenging. Several existing approaches utilize linear relaxation based neural network output bounds under perturbation, but they can slow down training by a factor of…

机器学习 · 计算机科学 2019-11-28 Huan Zhang , Hongge Chen , Chaowei Xiao , Sven Gowal , Robert Stanforth , Bo Li , Duane Boning , Cho-Jui Hsieh

While Graph Neural Networks (GNNs) have achieved remarkable success, their design largely relies on empirical intuition rather than theoretical understanding. In this paper, we present a comprehensive analysis of GNN behavior through three…

机器学习 · 计算机科学 2025-02-04 Qin Jiang , Chengjia Wang , Michael Lones , Wei Pang

Belief propagation has recently emerged as a powerful framework for evaluating tensor networks in higher dimensions, combining computational efficiency with provable analytical guarantees. In this work, we develop the first end-to-end…

量子物理 · 物理学 2026-04-24 Siddhant Midha , Yifan F. Zhang , Daniel Malz , Dmitry A. Abanin , Sarang Gopalakrishnan

K-Nearest Neighbours (k-NN) is a popular classification and regression algorithm, yet one of its main limitations is the difficulty in choosing the number of neighbours. We present a Bayesian algorithm to compute the posterior probability…

机器学习 · 计算机科学 2017-06-05 Giuseppe Nuti

The canonical problem of solving a system of linear equations arises in numerous contexts in information theory, communication theory, and related fields. In this contribution, we develop a solution based upon Gaussian belief propagation…

信息论 · 计算机科学 2009-07-12 Danny Bickson

Belief propagation -- a powerful heuristic method to solve inference problems involving a large number of random variables -- was recently generalized to quantum theory. Like its classical counterpart, this algorithm is exact on trees when…

量子物理 · 物理学 2009-11-13 David Poulin , Ersen Bilgin

Inference for probabilistic graphical models is still very much a practical challenge in large domains. The commonly used and effective belief propagation (BP) algorithm and its generalizations often do not converge when applied to hard,…

人工智能 · 计算机科学 2012-07-02 Gal Elidan , Ian McGraw , Daphne Koller

In this paper, deep neural network (DNN) is utilized to improve the belief propagation (BP) detection for massive multiple-input multiple-output (MIMO) systems. A neural network architecture suitable for detection task is firstly introduced…

信号处理 · 电气工程与系统科学 2018-04-06 Xiaosi Tan , Weihong Xu , Yair Be'ery , Zaichen Zhang , Xiaohu You , Chuan Zhang

Using graph neural networks for large graphs is challenging since there is no clear way of constructing mini-batches. To solve this, previous methods have relied on sampling or graph clustering. While these approaches often lead to good…

机器学习 · 计算机科学 2022-12-20 Johannes Gasteiger , Chendi Qian , Stephan Günnemann

Belief propagation (BP) provides a scalable heuristic for contracting tensor networks on loopy graphs, but its success in quantum many-body settings has largely rested on empirical evidence. Developing upon a recently introduced…

量子物理 · 物理学 2026-04-06 Siddhant Midha , Grace M. Sommers , Joseph Tindall , Dmitry A. Abanin

Describing nonequilibrium quantum dynamics remains a significant computational challenge due to the growth of spatial entanglement. The tensor network influence functional (TN-IF) approach mitigates this problem for computing the time…

量子物理 · 物理学 2025-11-26 Gunhee Park , Johnnie Gray , Garnet Kin-Lic Chan

A major benefit of graphical models is that most knowledge is captured in the model structure. Many models, however, produce inference problems with a lot of symmetries not reflected in the graphical structure and hence not exploitable by…

人工智能 · 计算机科学 2012-05-14 Kristian Kersting , Babak Ahmadi , Sriraam Natarajan

Although probabilistic inference in a general Bayesian belief network is an NP-hard problem, computation time for inference can be reduced in most practical cases by exploiting domain knowledge and by making approximations in the knowledge…

人工智能 · 计算机科学 2016-11-04 Alexander V. Kozlov , Jaswinder Pal Singh

Belief propagation (BP) is a message-passing heuristic for statistical inference in graphical models such as Bayesian networks and Markov random fields. BP is used to compute marginal distributions or maximum likelihood assignments and has…

数据结构与算法 · 计算机科学 2012-11-15 Tobias Brunsch , Kamiel Cornelissen , Bodo Manthey , Heiko Röglin