AI Paper Atlas

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

Beyond Worst-case: A Probabilistic Analysis of Affine Policies in Dynamic Optimization

Omar El Housni, Vineet Goyal

NeurIPS 2017 · Learning theory and algorithms › Combinatorial and search optimization · approach: Decision-focused optimization · 5 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 affine policy instead of optimal adjustable policyAffine policy · Uniform and Gaussian distributionsoptimality gap: at most 4%Mixed
use affine policy instead of MIP adjustable policy for m=30 (uniform)Affine policy · Uniform, m=30running time (s): 761.21 -> 1.29Improved
use affine policy instead of MIP adjustable policy for m=20 (folded normal)Affine policy · Folded Normal, m=20running time (s): 217.08 -> 0.39Improved
increase m to 50Adjustable policy MIP · Uniform and Folded NormalsolvabilityHurt
increase m to 50Affine policy · Uniformrunning time (s): 1.29 -> 14.92Mixed
compare empirical ratio to theoretical boundAffine policy · Uniformapproximation ratio: 2 -> 1.04Improved

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