End-to-End Constrained Optimization Learning: A Survey (2021-03-30T00:00:00.000000Z)

TL;DR

This paper presents a conceptual review of the recent advancements in this emerging area of hybrid machine learning and optimization to predict fast, approximate, solutions to combinatorial problems and to enable structural logical inference.

Abstract

This paper surveys the recent attempts at leveraging machine learning to solve constrained optimization problems. It focuses on surveying the work on integrating combinatorial solvers and optimization methods with machine learning architectures. These approaches hold the promise to develop new hybrid machine learning and optimization methods to predict fast, approximate, solutions to combinatorial problems and to enable structural logical inference. This paper presents a conceptual review of the recent advancements in this emerging area.

Authors

James Kotary

1 papers

Ferdinando Fioretto

1 papers

P. V. Hentenryck

2 papers

TL;DR

Abstract

Authors

References71 items

Combinatorial optimization and reasoning with graph neural networks

Interior Point Solving for LP-based prediction+optimisation

Learning Active Constraints to Efficiently Solve Bilevel Problems.

Differentially Private and Fair Deep Learning: A Lagrangian Dual Approach

Combining Deep Learning and Optimization for Security-Constrained Optimal Power Flow

Hybrid Models for Learning to Branch

A General Large Neighborhood Search Framework for Solving Integer Linear Programs

Teaching the old dog new tricks: supervised learning with constraints

Learning with Differentiable Perturbed Optimizers

Lagrangian Duality for Constrained Deep Learning

Differentiation of Blackbox Combinatorial Solvers

Smart Predict-and-Optimize for Hard Combinatorial Optimization Problems

Combinatorial Optimization by Graph Pointer Networks and Hierarchical Reinforcement Learning

Predicting AC Optimal Power Flows: Combining Deep Learning and Lagrangian Dual Methods

MIPaaL: Mixed Integer Program as a Layer

Reinforcement Learning for Integer Programming: Learning to Cut

Exact Combinatorial Optimization with Graph Convolutional Neural Networks

An Efficient Graph Convolutional Network Technique for the Travelling Salesman Problem

An Investigation into Prediction + Optimisation for the Knapsack Problem

SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solver

Graph Neural Networks: A Review of Methods and Applications

Machine Learning for Combinatorial Optimization: a Methodological Tour d'Horizon

Melding the Data-Decisions Pipeline: Decision-Focused Learning for Combinatorial Optimization

Numerical Optimization

2018 IEEE Data Science Workshop (DSW)

2018 Power Systems Computation Conference (PSCC)

Attention, Learn to Solve Routing Problems!

Reinforcement Learning for Solving the Vehicle Routing Problem

Statistical Learning for DC Optimal Power Flow

Graph Attention Networks

Smart "Predict, then Optimize"

Learning to Run Heuristics in Tree Search

On learning and branching: a survey

The Mixing method: low-rank coordinate descent for semidefinite programming with diagonal constraints

Learning Combinatorial Optimization Algorithms over Graphs

OptNet: Differentiable Optimization as a Layer in Neural Networks

Task-based End-to-end Model Learning in Stochastic Optimization

Neural Combinatorial Optimization with Reinforcement Learning

Gap Safe screening rules for sparsity enforcing penalties

Learning to Branch in Mixed Integer Programming

Pointer Networks

Neural Machine Translation by Jointly Learning to Align and Translate

Convex optimization

Et al

Learning Restart Strategies

Attention!

“Neural” computation of decisions in optimization problems

Multiplier and gradient methods

Proceedings of the National Academy of Sciences

Learning with Differentiable Pertubed Optimizers

Elmachtoub and Paul Grigas

A Comprehensive Survey on Graph Neural Networks

Optimization

emergent

Revised note on learning algorithms for quadratic assignment with graph neural networks

In International conference on machine learning (ICML)

The Journal of Machine Learning Research

ICLR) Workshops

In Advances in Neural Information Processing Systems (NeurIPS)

Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI)

Deep Learning

Nature

The Graph Neural Network Model

(Journal of Optimization Theory and Applications,135(11):285-299)Optimal Control of an M/G/1/K Queueing System with combined F-policy and Startup Times

Handbook of Constraint Programming

On the stability of the Travelling Salesman Problem algorithm of Hopfield and Tank

Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning

Reinforcement Learning: An Introduction

A method for nonlinear constraints in minimization problems

ACTIVITY ANALYSIS OF PRODUCTION AND ALLOCATION

Maximization of a linear function of variables subject to linear inequalities

Field of Study

Journal Information

Name

Volume

Venue Information