AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

T2T: From Distribution Learning in Training to Gradient Search in Testing for Combinatorial Optimization

Yang Li, Jinpei Guo, Runzhong Wang, Junchi Yan

NeurIPS 2023 · Probabilistic and scientific modeling › Molecules and proteins · approach: Sparse concepts and hypothesis testing · 6 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 gradient search (1 iteration) (ablation)T2T · TSP-500 greedyperformance drop (%): 1.59% -> 0.94%Improved
increase gradient-search iterations from 1 to 3 (ablation)T2T · TSP-500 greedyperformance drop (%): 0.94% -> 0.80%Improved
increase gradient-search iterations from 3 to 10 (ablation)T2T · TSP-500 greedyperformance drop (%): 0.80% -> 0.72%Improved
increase graph sparsification k from 10 to 200 (ablation)T2T · TSP-500 greedyperformance drop (%): 0.83% -> 0.74%Improved
vary disruption ratio alpha (ablation)T2T · TSP-500 greedy and samplingperformance drop (%)Mixed
vary number of denoising steps for initial solution (ablation)T2T · TSP-500performance drop (%)No clear effect
add objective-guided gradient search to DIFUSCODIFUSCO · TSP-50 greedyperformance drop (%): 0.48% -> 0.04%Improved
add objective-guided gradient search to DIFUSCODIFUSCO · TSP-100 greedyperformance drop (%): 1.01% -> 0.18%Improved
add gradient search to DIFUSCODIFUSCO · TSP-500 greedyperformance drop (%): 9.41% -> 5.09%Improved
add gradient search to DIFUSCODIFUSCO · TSP-500 sampling+2OPTperformance drop (%): 0.83% -> 0.37%Improved
add gradient search to DIFUSCODIFUSCO · TSP-1000 sampling+2OPTperformance drop (%): 1.30% -> 0.78%Improved
add gradient search to DIFUSCODIFUSCO · TSPLIBperformance drop (%): 0.319% -> 0.133%Improved

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