Research map / Probabilistic and scientific modeling / Molecules and proteins
Launch and Iterate: Reducing Prediction Churn
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Add RCP stabilization operator | Ridge regression · Nomao | churn ratio: 1.00 -> 0.54 | Helped |
| Add RCP stabilization operator | SVM · Twitter Buzz | WLR: 1.35 -> 1.77 | Helped |
| Add RCP stabilization operator | SVM · Twitter Buzz | pwin: 42.2 -> 86.6 | Helped |
| Add RCP stabilization operator | Ridge · Twitter Buzz | WLR: 1.71 -> 3.54 | Helped |
| Add RCP stabilization operator | RF · Twitter Buzz | WLR: 1.35 -> 1.15 | Hurt |
| Add RCP stabilization operator | Ridge · News | WLR: 0.95 -> 0.94 | No clear effect |
| Add RCP stabilization operator | SVM · Nomao | WLR: 1.70 -> 2.51 | Helped |
| Run RCP inside MCMC chain (k=30) instead of single step | RCP · Twitter Buzz Ridge | churn ratio: 0.85 -> 0.65 ± 0.05 | Helped |
| MCMC instead of single step RCP | RCP · Twitter Buzz Ridge | WLR: 3.54 -> 1.53 | Hurt |
| MCMC stabilization | Ridge · Twitter Buzz | accuracy: 89.7 -> 90.1 ± 0.1 | Helped |
| Increase epsilon in RCP (ablation) | RCP on SVM · Nomao | churn ratio and accuracy | Mixed |
| Increase alpha in RCP (ablation) | RCP on SVM · Nomao | churn ratio and accuracy | Mixed |
Closest papers by meaning
- Building a stable classifier with the inflated argmax (NeurIPS 2024 · similarity 0.84)
- A hierarchical decomposition for explaining ML performance discrepancies (NeurIPS 2024 · similarity 0.83)
- The Stability of Online Algorithms in Performative Prediction (NeurIPS 2026 · similarity 0.82)
- Treasure Hunt: Real-time Targeting of the Long Tail using Training-Time Markers (NeurIPS 2025 · similarity 0.82)
- Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn (ICML 2025 · similarity 0.82)
- Algorithms with Calibrated Machine Learning Predictions (ICML 2025 · similarity 0.82)
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.