Abstract:We study the predict+optimise problem, where machine learning and combinatorial optimisation must interact to achieve a common goal. These problems are important when optimisation needs to be performed on input parameters that are not fully observed but must instead be estimated using machine learning. Our contributions are two-fold: 1) we provide theoretical insight into the properties and computational complexity of predict+optimise problems in general, and 2) develop a novel framework that, in contrast to r… Show more
“…We want to maximize the revenue we get but we need to predict half-hour prices. We use real-world energy-aware scheduling data from (Demirovic et al 2019) which consist of historical energy data and prices from the ICON energy-aware scheduling competition. The time period weights are drawn uniformly between 0 and 1, and the budget is 10% of the total weight.…”
Section: Benchmark Problemsmentioning
confidence: 99%
“…The time period weights are drawn uniformly between 0 and 1, and the budget is 10% of the total weight. In (Demirovic et al 2019), the authors describe and analyze an algorithm for exhaustively searching linear models which yield good knapsack performance; however, the results are for linear predictive components feeding to knapsack instances, and do not directly extend to neural network models.…”
Section: Benchmark Problemsmentioning
confidence: 99%
“…MIPs naturally arise in so many settings largely due to their flexibility, computational complexity (ability to capture NPhard problems), and interpretability. In many practical situations it is often necessary to predict some component (e.g., the objective) of the MIP based on historical data, such as estimated demand (O'Mahony and Shmoys 2015), price forecasts (Demirovic et al 2019), or patient readmission rate (Chan et al 2012). Alternatively, practitioners may use a MIP to enforce that the outputs of the predictions meet semantically meaningful objectives such as ensuring predictions result in making fair decisions downstream (Benabbou et al 2018;Trilling, Guinet, and Le Magny 2006;Warner 1976).…”
Machine learning components commonly appear in larger decision-making pipelines; however, the model training process typically focuses only on a loss that measures average accuracy between predicted values and ground truth values. Decision-focused learning explicitly integrates the downstream decision problem when training the predictive model, in order to optimize the quality of decisions induced by the predictions. It has been successfully applied to several limited combinatorial problem classes, such as those that can be expressed as linear programs (LP), and submodular optimization. However, these previous applications have uniformly focused on problems with simple constraints. Here, we enable decision-focused learning for the broad class of problems that can be encoded as a mixed integer linear program (MIP), hence supporting arbitrary linear constraints over discrete and continuous variables. We show how to differentiate through a MIP by employing a cutting planes solution approach, an algorithm that iteratively tightens the continuous relaxation by adding constraints removing fractional solutions. We evaluate our new end-to-end approach on several real world domains and show that it outperforms the standard two phase approaches that treat prediction and optimization separately, as well as a baseline approach of simply applying decision-focused learning to the LP relaxation of the MIP. Lastly, we demonstrate generalization performance in several transfer learning tasks.
“…We want to maximize the revenue we get but we need to predict half-hour prices. We use real-world energy-aware scheduling data from (Demirovic et al 2019) which consist of historical energy data and prices from the ICON energy-aware scheduling competition. The time period weights are drawn uniformly between 0 and 1, and the budget is 10% of the total weight.…”
Section: Benchmark Problemsmentioning
confidence: 99%
“…The time period weights are drawn uniformly between 0 and 1, and the budget is 10% of the total weight. In (Demirovic et al 2019), the authors describe and analyze an algorithm for exhaustively searching linear models which yield good knapsack performance; however, the results are for linear predictive components feeding to knapsack instances, and do not directly extend to neural network models.…”
Section: Benchmark Problemsmentioning
confidence: 99%
“…MIPs naturally arise in so many settings largely due to their flexibility, computational complexity (ability to capture NPhard problems), and interpretability. In many practical situations it is often necessary to predict some component (e.g., the objective) of the MIP based on historical data, such as estimated demand (O'Mahony and Shmoys 2015), price forecasts (Demirovic et al 2019), or patient readmission rate (Chan et al 2012). Alternatively, practitioners may use a MIP to enforce that the outputs of the predictions meet semantically meaningful objectives such as ensuring predictions result in making fair decisions downstream (Benabbou et al 2018;Trilling, Guinet, and Le Magny 2006;Warner 1976).…”
Machine learning components commonly appear in larger decision-making pipelines; however, the model training process typically focuses only on a loss that measures average accuracy between predicted values and ground truth values. Decision-focused learning explicitly integrates the downstream decision problem when training the predictive model, in order to optimize the quality of decisions induced by the predictions. It has been successfully applied to several limited combinatorial problem classes, such as those that can be expressed as linear programs (LP), and submodular optimization. However, these previous applications have uniformly focused on problems with simple constraints. Here, we enable decision-focused learning for the broad class of problems that can be encoded as a mixed integer linear program (MIP), hence supporting arbitrary linear constraints over discrete and continuous variables. We show how to differentiate through a MIP by employing a cutting planes solution approach, an algorithm that iteratively tightens the continuous relaxation by adding constraints removing fractional solutions. We evaluate our new end-to-end approach on several real world domains and show that it outperforms the standard two phase approaches that treat prediction and optimization separately, as well as a baseline approach of simply applying decision-focused learning to the LP relaxation of the MIP. Lastly, we demonstrate generalization performance in several transfer learning tasks.
“…We find that typical datasets only contain a set of sampled attacker responses to a particular historical defender mixed strategy or a small set of mixed strategies. Previous work on end-to-end learning for decision problems (Bengio 1997;Donti, Amos, and Kolter 2017;Wilder, Dilkina, and Tambe 2019;Demirovic et al 2019) assumes that the historical data specifies the utility of any possible decision, but this assumption does not hold in SSGs because they are interactions between strategic agents.…”
“…This analytic approach is extended to stochastic optimization by Donti et al (2017) and to submodular optimization by Wilder et al (2019). Demirovic et al (2019) provide a theoretically optimal framework for ranking problems with linear objectives.…”
Stackelberg security games are a critical tool for maximizing the utility of limited defense resources to protect important targets from an intelligent adversary. Motivated by green security, where the defender may only observe an adversary's response to defense on a limited set of targets, we study the problem of learning a defense that generalizes well to a new set of targets with novel feature values and combinations. Traditionally, this problem has been addressed via a two-stage approach where an adversary model is trained to maximize predictive accuracy without considering the defender's optimization problem. We develop an end-to-end game-focused approach, where the adversary model is trained to maximize a surrogate for the defender's expected utility. We show both in theory and experimental results that our game-focused approach achieves higher defender expected utility than the two-stage alternative when there is limited data.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.