Combinatorial Optimization

260 papers with code • 0 benchmarks • 2 datasets

Combinatorial Optimization is a category of problems which requires optimizing a function over a combination of discrete objects and the solutions are constrained. Examples include finding shortest paths in a graph, maximizing value in the Knapsack problem and finding boolean settings that satisfy a set of constraints. Many of these problems are NP-Hard, which means that no polynomial time solution can be developed for them. Instead, we can only produce approximations in polynomial time that are guaranteed to be some factor worse than the true optimal solution.

Source: Recent Advances in Neural Program Synthesis


Use these libraries to find Combinatorial Optimization models and implementations

Most implemented papers

Pointer Networks

devsisters/pointer-network-tensorflow NeurIPS 2015

It differs from the previous attention attempts in that, instead of using attention to blend hidden units of an encoder to a context vector at each decoder step, it uses attention as a pointer to select a member of the input sequence as the output.

Attention, Learn to Solve Routing Problems!

wouterkool/attention-learn-to-route ICLR 2019

The recently presented idea to learn heuristics for combinatorial optimization problems is promising as it can save costly development.

Neural Combinatorial Optimization with Reinforcement Learning

pemami4911/neural-combinatorial-rl-pytorch 29 Nov 2016

Despite the computational expense, without much engineering and heuristic designing, Neural Combinatorial Optimization achieves close to optimal results on 2D Euclidean graphs with up to 100 nodes.

Solving the Rubik's Cube Without Human Knowledge

AashrayAnand/rubiks-cube-reinforcement-learning 18 May 2018

A generally intelligent agent must be able to teach itself how to solve problems in complex domains with minimal human supervision.

Learning Combinatorial Optimization Algorithms over Graphs

Hanjun-Dai/graph_comb_opt NeurIPS 2017

The design of good heuristics or approximation algorithms for NP-hard combinatorial optimization problems often requires significant specialized knowledge and trial-and-error.

Exact Combinatorial Optimization with Graph Convolutional Neural Networks

ds4dm/learn2branch NeurIPS 2019

Combinatorial optimization problems are typically tackled by the branch-and-bound paradigm.

Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers

martius-lab/blackbox-deep-graph-matching 25 Mar 2020

Building on recent progress at the intersection of combinatorial optimization and deep learning, we propose an end-to-end trainable architecture for deep graph matching that contains unmodified combinatorial solvers.

Reinforcement Learning for Solving the Vehicle Routing Problem

OptMLGroup/VRP-RL NeurIPS 2018

Our model represents a parameterized stochastic policy, and by applying a policy gradient algorithm to optimize its parameters, the trained model produces the solution as a sequence of consecutive actions in real time, without the need to re-train for every new problem instance.

Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsing

crazydonkey200/neural-symbolic-machines NeurIPS 2018

We present Memory Augmented Policy Optimization (MAPO), a simple and novel way to leverage a memory buffer of promising trajectories to reduce the variance of policy gradient estimate.

Learning the Travelling Salesperson Problem Requires Rethinking Generalization

chaitjo/learning-tsp 12 Jun 2020

End-to-end training of neural network solvers for graph combinatorial optimization problems such as the Travelling Salesperson Problem (TSP) have seen a surge of interest recently, but remain intractable and inefficient beyond graphs with few hundreds of nodes.