AI Paper Atlas

Research map / Optimization / Optimizers

Learning to Optimize in Swarms

Yue Cao, Tianlong Chen, Zhangyang Wang, Yang Shen

NeurIPS 2019 · Optimization › Optimizers · approach: Gradient-based meta-learning theory · 14 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
Run k independently initialized DM_LSTMs and select the best solution (ablation)DM_LSTM · Rastrigin 10Dminimum objective: 55.4±13.5 -> 48.4±10.5No clear effect
Run k independently initialized DM_LSTMs and select the best solution (ablation)DM_LSTM · Rastrigin 20Dminimum objective: 140.4±10.2 -> 137.4±12.7No clear effect
Add point-based features and intra-particle attention to independent particles (ablation)B1 · Rastrigin 10Dminimum objective: 48.4±10.5 -> 40.1±9.4Improved
Add point-based features and intra-particle attention to independent particles (ablation)B1 · Rastrigin 20Dminimum objective: 137.4±12.7 -> 108.4±13.4Improved
Add population-based features and inter-particle attention to create a swarm (ablation)B2 · Rastrigin 10Dminimum objective: 40.1±9.4 -> 20.4±6.6Improved
Add population-based features and inter-particle attention to create a swarm (ablation)B2 · Rastrigin 20Dminimum objective: 108.4±13.4 -> 48.5±7.1Improved
Add the posterior entropy term to the meta-loss (ablation)B3 · Rastrigin 10Dminimum objective: 20.4±6.6 -> 12.3±5.4Improved
Add the posterior entropy term to the meta-loss (ablation)B3 · Rastrigin 20Dminimum objective: 48.5±7.1 -> 43.0 ±9.2Improved

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