Research map / Architectures and efficiency / Mixture of experts
Why Ask One When You Can Ask $k$? Learning-to-Defer to the Top-$k$ Experts
Yannis Montreuil, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi
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 |
|---|---|---|---|
| use adaptive Top-k(x) instead of fixed Top-k (min RMSE metric) (ablation) | Top-k L2D, two-stage · California Housing | RMSE and budget: RMSE 6.23 at budget 0.156 (4.77 entities) vs 6.21 at budget 0.2 (6 entities) | Improved |
| use adaptive Top-k(x) instead of fixed Top-k (uniform average RMSE) (ablation) | Top-k L2D, two-stage · California Housing | RMSE_avg: 10.08 -> 8.53 | Improved |
| consult more or costlier entities under average-based metrics (ablation) | Top-k L2D · California Housing, RMSE_avg and RMSE_w-avg | RMSE | Hurt |
| defer to top-k experts (k>1) instead of a single expert | Top-1 L2D baseline · California Housing | RMSE | Improved |
Closest papers by meaning
- Mastering Multiple-Expert Routing: Realizable $H$-Consistency and Strong Guarantees for Learning to Defer (ICML 2025 · similarity 0.87)
- When to Act and When to Ask: Policy Learning With Deferral Under Hidden Confounding (NeurIPS 2024 · similarity 0.85)
- Principled Bayesian Optimization in Collaboration with Human Experts (NeurIPS 2024 · similarity 0.85)
- A Unifying Post-Processing Framework for Multi-Objective Learn-to-Defer Problems (NeurIPS 2024 · similarity 0.84)
- Regression with Multi-Expert Deferral (ICML 2024 · similarity 0.84)
- When Lower-Order Terms Dominate: Adaptive Expert Algorithms for Heavy-Tailed Losses (NeurIPS 2025 · similarity 0.84)
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.
