Pith. sign in

REVIEW 6 cited by

Differentiation of Blackbox Combinatorial Solvers

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1912.02175 v2 pith:4DXVYBLB submitted 2019-12-04 cs.LG stat.ML

classification cs.LGstat.ML
keywords combinatorialproblemalgorithmarchitecturesblackboxsolversachievingalgorithms
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Achieving fusion of deep learning with combinatorial algorithms promises transformative changes to artificial intelligence. One possible approach is to introduce combinatorial building blocks into neural networks. Such end-to-end architectures have the potential to tackle combinatorial problems on raw input data such as ensuring global consistency in multi-object tracking or route planning on maps in robotics. In this work, we present a method that implements an efficient backward pass through blackbox implementations of combinatorial solvers with linear objective functions. We provide both theoretical and experimental backing. In particular, we incorporate the Gurobi MIP solver, Blossom V algorithm, and Dijkstra's algorithm into architectures that extract suitable features from raw inputs for the traveling salesman problem, the min-cost perfect matching problem and the shortest path problem. The code is available at https://github.com/martius-lab/blackbox-backprop.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Decision-Aware Approximation of Belief Functions for Evidential Combinatorial Optimization

    cs.AI 2026-08 conditional novelty 6.0 of 10

    A decision-aware belief function compressor targets the regret of the induced combinatorial decision, with a one-point regret bound and an exact scalar dynamic program, and flips the decision less often than represent...

  2. Decision-Focused Learning in Network Interdiction Games

    cs.GT 2026-08 conditional novelty 6.0 of 10

    A zero-loss equivalence class of cost estimators makes decision-focused learning fail in shortest-path network interdiction games, and training on interdicted scenarios (A-DFL) collapses this class and restores performance.

  3. Aligning Learning and Endogenous Decision-Making

    cs.LG 2025-07 reject novelty 6.0 of 10

    A decision-aware loss and robust uncertainty-set method for learning under endogenous uncertainty, plus a two-stage information-gathering extension, with experiments on pricing, assortment, and power scheduling.

  4. Position: Stop Reactively Patching Your Model Every Time and Start Proactive Test-Driven AI Development

    cs.LG 2026-07 conditional novelty 5.0 of 10

    In a stylized model, a proactive flywheel that fixes whole groups of related scenarios needs Θ(K log K) update rounds versus Θ(M log M) for reactive patching.

  5. Hidden Representation Clustering with Multi-Task Representation Learning towards Robust Online Budget Allocation

    cs.LG 2025-06 conditional novelty 5.0 of 10

    Budget allocation by clustering users in a learned hidden representation space and optimizing per cluster improves order volume and gross merchandise volume by up to 0.65% relative to individual-level baselines in Mei...

  6. Efficient End-to-End Learning for Decision-Making: A Meta-Optimization Approach

    cs.LG 2025-05 conditional novelty 5.0 of 10

    ProjectNet learns a matrix-parameterized update rule that approximates optimization solutions in a few forward steps, and using this surrogate in end-to-end training cuts training time by 2 to 10 times while keeping d...

Pith tools