AI Paper Atlas

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

Approximation Guarantees of Local Search Algorithms via Localizability of Set Functions

Kaito Fujii

ICML 2020 · Learning theory and algorithms › Combinatorial and search optimization · approach: Heuristic and local search 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
Use non-oblivious local search instead of oblivious local searchSparse regression, n=200 · Synthetic sparse regression, n=200running time: approximately 10 times fasterImproved
Use non-oblivious local search instead of oblivious local searchSparse regression, n=200 · Synthetic sparse regression, n=200R^2No clear effect
Use non-oblivious local search instead of random residual greedySparse regression · Synthetic sparse regression, n=200R^2Improved
Use non-oblivious local search instead of the benchmarksSparse regression · Synthetic sparse regression, n=1000R^2Improved
Use non-oblivious local search instead of modular approximationGraphical model structure learning · Ising models, |V|=10running timeNo clear effect
Use non-oblivious local search instead of modular approximationGraphical model structure learning · Ising models, |V|=10objective ratioImproved
Use non-oblivious local search instead of the benchmarksGraphical model structure learning · Ising models, |V|=20objective ratioImproved

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