PyEPO: A PyTorch-based End-to-End Predict-then-Optimize Tool

Learning Framework

Publication

This repository is the official implementation of the paper: PyEPO: A PyTorch-based End-to-End Predict-then-Optimize Library for Linear and Integer Programming

Citation:

@article{tang2022pyepo,
  title={PyEPO: A PyTorch-based End-to-End Predict-then-Optimize Library for Linear and Integer Programming},
  author={Tang, Bo and Khalil, Elias B},
  journal={arXiv preprint arXiv:2206.14234},
  year={2022}
}

Introduction

PyEPO (PyTorch-based End-to-End Predict-then-Optimize Tool) is a Python-based, open-source software that supports modeling and solving predict-then-optimize problems with the linear objective function. The core capability of PyEPO is to build optimization models with GurobiPy, Pyomo, or any other solvers and algorithms, then embed the optimization model into an artificial neural network for the end-to-end training. For this purpose, PyEPO implements smart predict-then-optimize+ loss [1], differentiable Black-Box optimizer [3], differentiable perturbed optimizer, Fenchel-Young loss with Perturbation [4], noise-contrastive estimation [5] and learning to rank losses [6] as PyTorch autograd modules.

Documentation

The official PyEPO docs can be found at https://khalil-research.github.io/PyEPO.

Tutorial

01 Optimization Model: Build up optimization solver
02 Optimization Dataset: Generate synthetic data and use optDataset
03 Training and Testing: Train and test end-to-end predict-then-optimize for different approaches
04 2D knapsack Solution Visualization: Visualize solutions for knapsack problem
05 Warcraft Shortest Path: Use the Warcraft terrains dateset to train shortest path

Experiments

To reproduce the experiments in original paper, please use the code and follow the instruction in this branch.

Features

Implement SPO+ [1], DBB [3], DPO [4], PFYL [4], NCE [5] and LTR [6].
Support Gurobi and Pyomo API
Support Parallel computing for optimization solver
Support solution caching [5] to speed up training

Installation

You can download PyEPO from our GitHub repository.

git clone https://github.com/khalil-research/PyEPO.git

And install it.

pip install PyEPO/pkg/.

Dependencies

Issue

On Windows system, there is missing freeze_support to run multiprocessing directly from __main__. When processes is not 1, try if __name__ == "__main__": instead of Jupyter notebook or a PY file.

Sample Code

#!/usr/bin/env python
# coding: utf-8

import gurobipy as gp
from gurobipy import GRB
import numpy as np
import pyepo
from pyepo.model.grb import optGrbModel
import torch
from torch import nn
from torch.utils.data import DataLoader


# optimization model
class myModel(optGrbModel):
    def __init__(self, weights):
        self.weights = np.array(weights)
        self.num_item = len(weights[0])
        super().__init__()

    def _getModel(self):
        # ceate a model
        m = gp.Model()
        # varibles
        x = m.addVars(self.num_item, name="x", vtype=GRB.BINARY)
        # model sense
        m.modelSense = GRB.MAXIMIZE
        # constraints
        m.addConstr(gp.quicksum([self.weights[0,i] * x[i] for i in range(self.num_item)]) <= 7)
        m.addConstr(gp.quicksum([self.weights[1,i] * x[i] for i in range(self.num_item)]) <= 8)
        m.addConstr(gp.quicksum([self.weights[2,i] * x[i] for i in range(self.num_item)]) <= 9)
        return m, x


# prediction model
class LinearRegression(nn.Module):

    def __init__(self):
        super(LinearRegression, self).__init__()
        self.linear = nn.Linear(num_feat, num_item)

    def forward(self, x):
        out = self.linear(x)
        return out


if __name__ == "__main__":

    # generate data
    num_data = 1000 # number of data
    num_feat = 5 # size of feature
    num_item = 10 # number of items
    weights, x, c = pyepo.data.knapsack.genData(num_data, num_feat, num_item,
                                                dim=3, deg=4, noise_width=0.5, seed=135)

    # init optimization model
    optmodel = myModel(weights)

    # init prediction model
    predmodel = LinearRegression()
    # set optimizer
    optimizer = torch.optim.Adam(predmodel.parameters(), lr=1e-2)
    # init SPO+ loss
    spop = pyepo.func.SPOPlus(optmodel, processes=1)

    # build dataset
    dataset = pyepo.data.dataset.optDataset(optmodel, x, c)
    # get data loader
    dataloader = DataLoader(dataset, batch_size=32, shuffle=True)

    # training
    num_epochs = 10
    for epoch in range(num_epochs):
        for data in dataloader:
            x, c, w, z = data
            # forward pass
            cp = predmodel(x)
            loss = spop(cp, c, w, z).mean()
            # backward pass
            optimizer.zero_grad()
            loss.backward()
            optimizer.step()

    # eval
    regret = pyepo.metric.regret(predmodel, optmodel, dataloader)
    print("Regret on Training Set: {:.4f}".format(regret))

JayMan91/PyEPO