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
Signed reviews
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.
Forward citations
Cited by 6 Pith papers
-
Decision-Aware Approximation of Belief Functions for Evidential Combinatorial Optimization
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...
-
Decision-Focused Learning in Network Interdiction Games
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.
-
Aligning Learning and Endogenous Decision-Making
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.
-
Position: Stop Reactively Patching Your Model Every Time and Start Proactive Test-Driven AI Development
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.
-
Hidden Representation Clustering with Multi-Task Representation Learning towards Robust Online Budget Allocation
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...
-
Efficient End-to-End Learning for Decision-Making: A Meta-Optimization Approach
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...
Discussion (0). Continue with ORCID to comment.