@article{Wilder_Dilkina_Tambe_2019, title={Melding the Data-Decisions Pipeline: Decision-Focused Learning for Combinatorial Optimization}, volume={33}, url={https://ojs.aaai.org/index.php/AAAI/article/view/3982}, DOI={10.1609/aaai.v33i01.33011658}, abstractNote={<p>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).</p><p>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 highquality decisions. Technically, our contribution is a means of integrating common classes of 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 decisionfocused 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.</p>}, number={01}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Wilder, Bryan and Dilkina, Bistra and Tambe, Milind}, year={2019}, month={Jul.}, pages={1658-1665} }