Learning a Large Neighborhood Search Algorithm for Mixed Integer Programs

by   Nicolas Sonnerat, et al.

Large Neighborhood Search (LNS) is a combinatorial optimization heuristic that starts with an assignment of values for the variables to be optimized, and iteratively improves it by searching a large neighborhood around the current assignment. In this paper we consider a learning-based LNS approach for mixed integer programs (MIPs). We train a Neural Diving model to represent a probability distribution over assignments, which, together with an off-the-shelf MIP solver, generates an initial assignment. Formulating the subsequent search steps as a Markov Decision Process, we train a Neural Neighborhood Selection policy to select a search neighborhood at each step, which is searched using a MIP solver to find the next assignment. The policy network is trained using imitation learning. We propose a target policy for imitation that, given enough compute resources, is guaranteed to select the neighborhood containing the optimal next assignment amongst all possible choices for the neighborhood of a specified size. Our approach matches or outperforms all the baselines on five real-world MIP datasets with large-scale instances from diverse applications, including two production applications at Google. It achieves 2× to 37.8× better average primal gap than the best baseline on three of the datasets at large running times.


page 1

page 2

page 3

page 4


Solving Mixed Integer Programs Using Neural Networks

Mixed Integer Programming (MIP) solvers rely on an array of sophisticate...

Learning Large Neighborhood Search for Vehicle Routing in Airport Ground Handling

Dispatching vehicle fleets to serve flights is a key task in airport gro...

Optimizing Wi-Fi Channel Selection in a Dense Neighborhood

In dense neighborhoods, there are often dozens of homes in close proximi...

A note on 'Variable Neighborhood Search Based Algorithms for Crossdock Truck Assignment'

Some implementations of variable neighborhood search based algorithms we...

Adaptive Constraint Partition based Optimization Framework for Large-scale Integer Linear Programming(Student Abstract)

Integer programming problems (IPs) are challenging to be solved efficien...

Searching Large Neighborhoods for Integer Linear Programs with Contrastive Learning

Integer Linear Programs (ILPs) are powerful tools for modeling and solvi...

Multidimensional Assignment Problem for multipartite entity resolution

Multipartite entity resolution aims at integrating records from multiple...

Please sign up or login with your details

Forgot password? Click here to reset