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

09/14/2018
by   Bryan Wilder, et al.
0

Creating impact in real-world settings requires artificial intelligence techniques to span the full pipeline from data, to predictive models, to decisions. These components are typically approached separately: a machine learning model is first trained via a measure of predictive accuracy, and then its predictions are used as input into an optimization algorithm which produces a decision. However, the loss function used to train the model may easily be misaligned with the end goal, which is to make the best decisions possible. Hand-tuning the loss function to align with optimization is a difficult and error-prone process (which is often skipped entirely). We focus on combinatorial optimization problems and introduce a general framework for decision-focused learning, where the machine learning model is directly trained in conjunction with the optimization algorithm to produce high-quality decisions. Technically, our contribution is a means of integrating discrete optimization problems into deep learning or other predictive models, which are typically trained via gradient descent. The main idea is to use a continuous relaxation of the discrete problem to propagate gradients through the optimization procedure. We instantiate this framework for two broad classes of combinatorial problems: linear programs and submodular maximization. Experimental results across a variety of domains show that decision-focused learning often leads to improved optimization performance compared to traditional methods. We find that standard measures of accuracy are not a reliable proxy for a predictive model's utility in optimization, and our method's ability to specify the true goal as the model's training objective yields substantial dividends across a range of decision problems.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/12/2019

MIPaaL: Mixed Integer Program as a Layer

Machine learning components commonly appear in larger decision-making pi...
research
01/02/2021

Integrated Optimization of Predictive and Prescriptive Tasks

In traditional machine learning techniques, the degree of closeness betw...
research
09/16/2019

Gumbel-softmax Optimization: A Simple General Framework for Combinatorial Optimization Problems on Graphs

Many problems in real life can be converted to combinatorial optimizatio...
research
07/15/2021

USCO-Solver: Solving Undetermined Stochastic Combinatorial Optimization Problems

Real-world decision-making systems are often subject to uncertainties th...
research
07/23/2022

Annealed Training for Combinatorial Optimization on Graphs

The hardness of combinatorial optimization (CO) problems hinders collect...
research
07/13/2022

Unsupervised Learning for Combinatorial Optimization with Principled Objective Relaxation

Using machine learning to solve combinatorial optimization (CO) problems...
research
03/31/2022

SimPO: Simultaneous Prediction and Optimization

Many machine learning (ML) models are integrated within the context of a...

Please sign up or login with your details

Forgot password? Click here to reset