Research map / Reinforcement learning / Visual and representation RL
Differentiable Learning Under Triage
Nastaran Okati, Abir De, Manuel Gomez Rodriguez
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add optimal triage policy to the full-automation model | full-automation sigmoid model · Synthetic sigmoid regression | average loss: 0.0053 -> 0.0020 | Improved |
| train the model under triage and use its own optimal triage policy | triage-trained sigmoid model · Synthetic sigmoid regression | average loss: 0.0020 -> 0.0009 | Improved |
| use triage policy optimal for the full-automation model with the triage-trained model (ablation) | triage-trained sigmoid model · Synthetic sigmoid regression | average loss: 0.0009 -> 0.0031 | Hurt |
Closest papers by meaning
- Learning-Augmented Algorithms with Explicit Predictors (NeurIPS 2024 · similarity 0.82)
- Human Expertise in Algorithmic Prediction (NeurIPS 2024 · similarity 0.82)
- Towards Understanding the Universality of Transformers for Next-Token Prediction (ICLR 2025 · similarity 0.81)
- Final-Model-Only Data Attribution with a Unifying View of Gradient-Based Methods (NeurIPS 2025 · similarity 0.81)
- The Stability of Online Algorithms in Performative Prediction (NeurIPS 2026 · similarity 0.81)
- DTZO: Distributed Trilevel Zeroth Order Learning with Provable Non-Asymptotic Convergence (ICML 2025 · similarity 0.80)
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.
