Neural Networks for Combinatorial Optimization: A Review of More Than a Decade of Research

By K. Smith‐Miles. 1999

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Optimization & Training

Citations in the corpus

Predicting Tactical Solutions to Operational Planning Problems under Imperfect Information (2018, methodology): “The application of ML to discrete optimization problems was the focus of an important research effort in the 1980’s and 1990’s (Smith, 1999).”
Attention Solves Your TSP (2018, methodology): “Attention layer Following the architecture by Vaswani et al. (2017), each attention layer consist of two sublayers: a multi-head attention (MHA) layer that executes message passing between the nodes and an node-wise fully connected feed-forward (FF) layer.”
Accelerating a Recurrent Neural Network to Finite-Time Convergence for Solving Time-Varying Sylvester Equation by Using a Sign-Bi-power Activation Function (2012, background): “In the past two decades, recurrent neural networks have received considerable studies in many scientiﬁc and engineering ﬁelds, such as signal processing [9], pattern classiﬁcation [10,11], control of chaos [12], optimization [13,14], etc.”
A Comprehensive Review of Stability Analysis of Continuous-Time Recurrent Neural Networks (2014, background): “APPROACHES based on recurrent neural networks for solving optimization problems, which use analog computation implemented on electronic devices to replace numerical computation realized by mathematical algorithms, have attracted considerable attention (see [102], [105], [131], [220], [233], [248], [”
Machine Learning for Combinatorial Optimization: a Methodological Tour d'Horizon (2018, background): “Earlier work from the nineties focused on Hopﬁeld neural networks and self organizing neural networks, the interested reader is referred to the survey of Smith (1999).”
Attention, Learn to Solve Routing Problems! (2018, unknown): “NNs have been applied to many related problems (Smith, 1999), although in most cases in an online manner, starting ‘from scratch’ and ‘learning’ a solution for every instance.”
Stochastic Optimization: a Review (2002, background): “For recent contrasting and complimentary reviews of leading stochastic optimization methods in the literatures of other fields, see, e.g., Dasgupta & Michalewicz (1997), Fourer (1998), Gray et al. (1997), Neumaier (2002), Pint ´ er (1996), Reeves (1999), Smith (1999) , and T ¨ orn et al. (1999).”
An Efficient Graph Convolutional Network Technique for the Travelling Salesman Problem (2019, methodology): “Due to the highly structured nature of these problems, neural networks have been used to learn approximate policies instead, especially for problems that are non-trivial to design heuristics for [Smith, 1999, Bengio et al., 2018].”
Portfolio selection using neural networks (2005, methodology): “While the latter are mainly used in Euclidean problems, the Hopfield networks have been widely applied in different classes of combinatorial optimisation problems [12].”
Neural networks in business: techniques and applications for the operations researcher (2000, background): “[6,20] for more details of this and other self-organising approaches to optimisation.”