AI Paper Atlas

Research map / Bandits and online learning / Online convex optimization and games

Minimum-Cost Network Flow with Dual Predictions

Zhiyang Chen, Hailong Yao, Xia Yin

AAAI 2026 · Bandits and online learning › Online convex optimization and games · approach: Learning-augmented online algorithms · 0 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
add learned fixed dual prediction to cost-scaling eps-relaxationeps-relaxation · Road networksrunning time: 12.74x average speedup (6.2 to 21.4x)Improved
add CNN-predicted dual to cost-scaling eps-relaxationeps-relaxation · Escape routingrunning time: 1.64x average (1.1 to 2.3x)Improved
add dual prediction on a large escape case where gain is smalleps-relaxation · Escape routing case 8running time (s): 293.837 -> 265.732Improved
use eps-relaxation with prediction vs network simplexeps-relaxation · Road networksrunning time: 12.08 -> 1.00 (normalized)Improved
increase synthetic prediction error up to completely erroneouseps-relaxation with prediction · synthetic perturbations (flow 03 NH)running time: grows with error, robust at worst caseHurt
train predictor with l-infinity loss instead of l2 (ablation)CNN predictor · Escape routingtrainingHurt

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