AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Learning-to-Optimize via Deep Unfolded Flows

Augustinos D Saravanos, Oswin So, H M Sabbir Ahmad, Chuchu Fan

ICML 2026 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Flow matching and flow sampling

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 FlowOptimizer instead of best baseline (MS-Adam) on power grid dispatchFlowOptimizer · Power Grid (n=50)Best(f(X_K))/f(mu_0): 0.05 -> 1.2e-3Improved
use FlowOptimizer instead of PSO on robotic arm IKFlowOptimizer · Robotic Arm (n=30)Best(f(X_K))/f(mu_0): 0.011 -> 0.007Improved
use FlowOptimizer instead of L2O-GD on supply chainFlowOptimizer · Supply Chain (n=80)Best(f(X_K))/f(mu_0): 0.027 -> 0.013Improved
population-level flow update instead of learned single-point GD steps (L2O-GD)FlowOptimizer · Ackley/Rastrigin/Levy 20Dbest f errorImproved
dimension-agnostic variant trained on 20D, deployed on 200DFlowOptimizer · Ackley 200D, Levy 200Dbest f errorImproved
add optional Gaussian base sampler (ablation)FlowOptimizer · benchmarksstabilityMixed
use CEM and random search on high-dimensional multimodal problemsCEM, RS · Ackley/Rastrigin/Levy 20Dbest f errorHurt

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