Research map / Architectures and efficiency / RNNs and normalization
CoRE-Learning with Look-Ahead and Immediate Resource Allocation
Jing Wang, Xi-Tong Liu, Zhi-Hua Zhou
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 look-ahead feasibility check (DKF) and adaptive slicing/UCB (LaiRA vs STA) | LaiRA · Mixed task bundle | successful tasks: 2 -> 6 | Improved |
| replace fixed exploration phase of LARA with LaiRA | LaiRA · Mixed task bundle | successful tasks: 3 -> 6 | Improved |
| use DKF for extrapolation vs LS/WLS/KF/M4 | LaiRA · Loss extrapolation, limited data | prediction error | Improved |
| DKF vs WLS when data exceeds 20% | LaiRA · Loss extrapolation | prediction error | No clear effect |
| DKF vs offline M4 estimator in compute time | DKF · Loss extrapolation | time per prediction: 2.98 -> 3.73e-3 | Improved |
| DKF vs other one-pass baselines in compute time | DKF · Loss extrapolation | time per prediction: 5.35e-4 -> 3.73e-3 | Hurt |
| remove UCB exploration (ablation) | LaiRA · Pure and mixed bundles | successful tasks | Improved |
| remove DKF look-ahead feasibility check (ablation) | LaiRA · Pure and mixed bundles | successful tasks | Improved |
| remove adaptive time slicing (PD) (ablation) | LaiRA · Pure and mixed bundles | successful tasks | No clear effect |
| add adaptive time slicing (PD) to reduce switches (ablation) | LaiRA · Pure and mixed bundles | task switches | Improved |
| LaiRA vs LARA task switching | LaiRA · Scalability, 10-100 tasks | total task switching | Improved |
Closest papers by meaning
- Learning with Adaptive Resource Allocation (ICML 2024 · similarity 0.90)
- ATA: Adaptive Task Allocation for Efficient Resource Management in Distributed Machine Learning (ICML 2025 · similarity 0.84)
- RCCDA: Adaptive Model Updates in the Presence of Concept Drift under a Constrained Resource Budget (NeurIPS 2025 · similarity 0.83)
- Delve into the Applicability of Advanced Optimizers for Multi-Task Learning (NeurIPS 2026 · similarity 0.82)
- Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws (ICLR 2025 · similarity 0.82)
- Prodigy: An Expeditiously Adaptive Parameter-Free Learner (ICML 2024 · 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.
