atlas

Research map / Learning theory and algorithms / Submodular and game algorithms

Optimizing Long-term Social Welfare in Recommender Systems: A Constrained Matching Approach

ICML 2020 · Learning theory and algorithms › Submodular and game algorithms · approach: Matching markets and welfare · 11 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 constrained matching that accounts for provider viability instead of myopic best-match recommendationRecommender system · Synthetic uniformAvg. Welfare: -2.41 ± 0.59 -> -1.23 ± 0.57Helped
Use constrained matching that accounts for provider viability instead of myopic best-match recommendationRecommender system · Synthetic uniformViable Providers: 43.80 ± 1.94 -> 48.00 ± 2.10Helped
Use constrained matching that accounts for provider viability instead of myopic best-match recommendationRecommender system · Synthetic skewedAvg. Welfare: -5.68 ± 0.61 -> -3.40 ± 1.10Helped
Use constrained matching that accounts for provider viability instead of myopic best-match recommendationRecommender system · Synthetic skewedViable Providers: 34.40 ± 1.96 -> 42.00 ± 3.35Helped
Increase discount factor from γ=0.1 to γ=1.0 (ablation)LP-RS · Synthetic skewedAvg. Welfare: 18.02 ± 1.05 -> 63.62 ± 3.58Helped
Increase discount factor from γ=0.1 to γ=1.0 (ablation)LP-RS · Synthetic skewedMax Regret: 7.24 ± 0.77 -> 37.89 ± 1.39Hurt

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