AI Paper Atlas

Research map / Learning theory and algorithms / Combinatorial and search optimization

SurCo: Learning Linear SURrogates for COmbinatorial Nonlinear Optimization Problems

Aaron M Ferber, Taoan Huang, Daochen Zha, Martin Schubert, Benoit Steiner, Bistra Dilkina, Yuandong Tian

ICML 2023 · Learning theory and algorithms › Combinatorial and search optimization · approach: Unsupervised neural combinatorial optimization · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use SurCo-zero instead of the domain heuristicNonlinear route planning · Loose deadlineon-time success rate: 4.5% times higher success ratesImproved
use SurCo-zero instead of the domain heuristicNonlinear route planning · Normal deadlineon-time success rate: 6.5% times higher success ratesImproved
use SurCo-zero instead of the domain heuristicNonlinear route planning · Tight deadlineon-time success rate: 8.5% times higher success ratesImproved
use SurCo-zero instead of the domain heuristicNonlinear route planning · Nonlinear route planningon-time success rateImproved
use SurCo-zero instead of the domain heuristicEmbedding table sharding · Embedding table shardinglatencyImproved
use SurCo-prior instead of SurCo-zeroEmbedding table sharding · Smaller instances (T≤40)latencyImproved
use SurCo-zero instead of SurCo-priorEmbedding table sharding · Larger instanceslatencyImproved
add instance-specific fine-tuning to the SurCo-prior initializationSurCo-hybrid · Embedding table shardinglatencyImproved
use SurCo-zero instead of Pass-ThroughInverse photonic design · Inverse photonic designvalid solution rateImproved
use SurCo-prior instead of Pass-ThroughInverse photonic design · Inverse photonic designruntime: two orders of magnitude less timeImproved
add instance-specific fine-tuning to the SurCo-prior initializationSurCo-hybrid · Inverse photonic designvalid solution rateImproved
use SurCo-zero instead of the domain heuristicNonlinear route planning · Nonlinear route planningruntimeNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy