Backpropagation through Combinatorial Algorithms: Identity with Projection Works

Abstract

Embedding discrete solvers as differentiable layers has given modern deep learning architectures combinatorial expressivity and discrete reasoning capabilities. The derivative of these solvers is zero or undefined, therefore a meaningful replacement is crucial for effective gradient-based learning. Prior works rely on smoothing the solver with input perturbations, relaxing the solver to continuous problems, or interpolating the loss landscape with techniques that typically require additional solver calls, introduce extra hyper-parameters, or compromise performance. We propose a principled approach to exploit the geometry of the discrete solution space to treat the solver as a negative identity on the backward pass and further provide a theoretical justification. Our experiments demonstrate that such a straightforward hyper-parameter-free approach is able to compete with previous more complex methods on numerous experiments such as backpropagation through discrete samplers, deep graph matching, and image retrieval. Furthermore, we substitute the previously proposed problem-specific and label-dependent margin with a generic regularization procedure that prevents cost collapse and increases robustness.

ICLR 2023 conference paper. The first two authors contributed equally

Cited by in corpus (6)

• A Survey of Contextual Optimization Methods for Decision Making under Uncertainty
• Decision-Focused Learning: Foundations, State of the Art, Benchmark and Future Opportunities
• Decision-Oriented Learning for Future Power System Decision-Making under Uncertainty
• One-step differentiation of iterative algorithms
• Robust Losses for Decision-Focused Learning
• Scalable Coupling of Deep Learning with Logical Reasoning