# Decision-Focused Learning without Differentiable Optimization: Learning Locally Optimized Decision Losses

arXiv: https://arxiv.org/abs/2203.16067 · HTML: https://mlsanity.com/paper/2203.16067/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 46 references that are in the map.
- First posted on arXiv 30 Mar 2022.

## Builds on (most cited first, 16 of 16)

- [Differentiable Convex Optimization Layers](https://mlsanity.com/paper/1910.12430/) (2019)
- [Smart "Predict, then Optimize"](https://mlsanity.com/paper/1710.08005/) (2017)
- [Melding the Data-Decisions Pipeline: Decision-Focused Learning for Combinatorial Optimization](https://mlsanity.com/paper/1809.05504/) (2018)
- [Differentiable MPC for End-to-end Planning and Control](https://mlsanity.com/paper/1810.13400/) (2018)
- [MIPaaL: Mixed Integer Program as a Layer](https://mlsanity.com/paper/1907.05912/) (2019)
- [Smart Predict-and-Optimize for Hard Combinatorial Optimization Problems](https://mlsanity.com/paper/1911.10092/) (2019)
- [Interior Point Solving for LP-based prediction+optimisation](https://mlsanity.com/paper/2010.13943/) (2020)
- [Differentiable Dynamic Programming for Structured Prediction and Attention](https://mlsanity.com/paper/1802.03676/) (2018)
- [Contrastive Losses and Solution Caching for Predict-and-Optimize](https://mlsanity.com/paper/2011.05354/) (2020)
- [End to end learning and optimization on graphs](https://mlsanity.com/paper/1905.13732/) (2019)
- [POPCORN: Partially Observed Prediction COnstrained ReiNforcement Learning](https://mlsanity.com/paper/2001.04032/) (2020)
- [The Limited Multi-Label Projection Layer](https://mlsanity.com/paper/1906.08707/) (2019)
- [Automatically Learning Compact Quality-aware Surrogates for Optimization Problems](https://mlsanity.com/paper/2006.10815/) (2020)
- [Differentiable Submodular Maximization](https://mlsanity.com/paper/1803.01785/) (2018)
- [The Perils of Learning Before Optimizing](https://mlsanity.com/paper/2106.10349/) (2021)
- [Divide and Learn: A Divide and Conquer Approach for Predict+Optimize](https://mlsanity.com/paper/2012.02342/) (2020)

## Built on by (most cited first, 12 of 12)

- [Gen-DFL: Decision-Focused Generative Learning for Robust Decision Making](https://mlsanity.com/paper/2502.05468/) (2025)
- [Decision-Focused Learning with Directional Gradients](https://mlsanity.com/paper/2402.03256/) (2024)
- [BPQP: A Differentiable Convex Optimization Framework for Efficient End-to-End Learning](https://mlsanity.com/paper/2411.19285/) (2024)
- [Solver-Free Decision-Focused Learning for Linear Optimization Problems](https://mlsanity.com/paper/2505.22224/) (2025)
- [Robust Losses for Decision-Focused Learning](https://mlsanity.com/paper/2310.04328/) (2023)
- [Decision-focused Graph Neural Networks for Combinatorial Optimization](https://mlsanity.com/paper/2406.03647/) (2024)
- [What is the Right Notion of Distance between Predict-then-Optimize Tasks?](https://mlsanity.com/paper/2409.06997/) (2024)
- [Generalized Decision Focused Learning under Imprecise Uncertainty--Theoretical Study](https://mlsanity.com/paper/2502.17984/) (2025)
- [A Dual Perspective on Decision-Focused Learning: Scalable Training via Dual-Guided Surrogates](https://mlsanity.com/paper/2511.04909/) (2025)
- [Differentiation of Multi-objective Data-driven Decision Pipeline](https://mlsanity.com/paper/2406.00779/) (2024)
- [Contrasting Cost-Agnostic and Cost-Sensitive Losses under Limited Model Capacity via mathcal H-consistency](https://mlsanity.com/paper/2502.19522/) (2025)
- [Exploring End-to-end Differentiable Neural Charged Particle Tracking -- A Loss Landscape Perspective](https://mlsanity.com/paper/2407.13420/) (2024)

## Abstract (arXiv)

Decision-Focused Learning (DFL) is a paradigm for tailoring a predictive model to a downstream optimization task that uses its predictions in order to perform better on that specific task. The main technical challenge associated with DFL is that it requires being able to differentiate through the optimization problem, which is difficult due to discontinuous solutions and other challenges. Past work has largely gotten around this issue by handcrafting task-specific surrogates to the original optimization problem that provide informative gradients when differentiated through. However, the need to handcraft surrogates for each new task limits the usability of DFL. In addition, there are often no guarantees about the convexity of the resulting surrogates and, as a result, training a predictive model using them can lead to inferior local optima. In this paper, we do away with surrogates altogether and instead learn loss functions that capture task-specific information. To the best of our knowledge, ours is the first approach that entirely replaces the optimization component of decision-focused learning with a loss that is automatically learned. Our approach (a) only requires access to a black-box oracle that can solve the optimization problem and is thus generalizable, and (b) can be convex by construction and so can be easily optimized over. We evaluate our approach on three resource allocation problems from the literature and find that our approach outperforms learning without taking into account task structure in all three domains, and even hand-crafted surrogates from the literature.