Data-Efficient Scaling-Law Discovery for Recommendation Systems via Coupled Hyperparameter Scaling
cs.LG, cs.IR
Submitted: 2026-11-03
Updated: 2026-11-03
Comments: 12 pages, 10 figures
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Understanding Scaling Laws for Recommendation Models
- Loss-to-Loss Prediction: Scaling Laws for All Datasets
- Efficiently Estimating Optimal Hyperparameter Scaling Laws through Power-Law Entropy Search
- Deep Learning Scaling is Predictable, Empirically
- Training Compute-Optimal Large Language Models
- Scaling Laws for Neural Language Models
- Re-Examining Linear Embeddings for High-Dimensional Bayesian Optimization
- (Mis)Fitting: A Survey of Scaling Laws
- Spend Less, Fit Better: Budget-Efficient Scaling Law Fitting via Active Experiment Selection
- Template-Driven Machine Learning Standardization for Large Model Fleets
- Deep Learning Recommendation Model for Personalization and Recommendation Systems
- Optimizing Sequential Recommendation Models with Scaling Laws and Approximate Entropy
- Freeze-Thaw Bayesian Optimization
- Scaling Laws for Online Advertisement Retrieval
- Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer
- Tensor Programs VI: Feature Learning in Infinite-Depth Neural Networks
- DHEN: A Deep and Hierarchical Ensemble Network for Large-Scale Click-Through Rate Prediction
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis