AI Paper Atlas

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

Landscape Surrogate: Learning Decision Losses for Mathematical Optimization Under Partial Information

Arman Zharmagambetov, Brandon Amos, Aaron M Ferber, Taoan Huang, Bistra Dilkina, Yuandong Tian

NeurIPS 2023 · Learning theory and algorithms › Combinatorial and search optimization · approach: Constrained neural network optimization · 2 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
reuse pretrained landscape surrogate M_w without solver access (ablation)LANCER-zero · Stochastic shortest path 15x15, normal deadlineruntime (s): 62.3 -> 2.7Improved
reuse pretrained landscape surrogate M_w without solver access (ablation)LANCER-zero · Stochastic shortest path 15x15, tight deadlineobjective: 0.434 -> 0.432No clear effect
reuse pretrained landscape surrogate M_w without solver access (ablation)LANCER-zero · Stochastic shortest path 15x15, loose deadlineobjective: 0.556 -> 0.556No clear effect
reduce M_w max iterations from 10 to 5 (lr 0.0005) (ablation)LANCER · Nonlinear shortest pathobjective: 0.4651 -> 0.4590Hurt
increase M_w max iterations from 10 to 20 (lr 0.001) (ablation)LANCER · Nonlinear shortest pathobjective: 0.4649 -> 0.4612Hurt
lower c_theta learning rate from 0.001 to 0.0005 (ablation)LANCER · Nonlinear shortest pathobjective: 0.4649 -> 0.4612Hurt
raise c_theta learning rate from 0.001 to 0.01 (ablation)LANCER · Nonlinear shortest pathobjective: 0.4649 -> 0.4650No clear effect
raise c_theta max iterations from 10 to 20 (ablation)LANCER · Nonlinear shortest pathobjective: 0.4649 -> 0.4648No clear effect
vary M_w depth and width from 1x50 to 3x200 (ablation)LANCER · Nonlinear shortest pathobjective: 0.4644 -> 0.4642No clear effect
use LANCER instead of MDFL, which uses exact gradientsLANCER · Portfolio selection (QP)normalized test decision loss: 0.52 -> 0.53Hurt
use LANCER instead of 2-StageLANCER · Portfolio selection (QP)normalized test decision loss: 0.57 -> 0.53Improved
use LANCER-zero instead of SurCo-zeroLANCER-zero · Nonlinear shortest pathobjectiveImproved

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