Cost-Aware Stopping for Freeze-Thaw Bayesian Optimization: When Does One-Step Lookahead Suffice?
cs.LG, math.OC, stat.ML
Submitted: 2026-10-30
Updated: 2026-10-30
Code: https://github.com/longvus/EIS
Terminology
Sources
- Matching with Nested and Bundled Pandora Boxes
- Combinatorial Markov Search
- Learning to select computations
- Roboflow 100: A Rich, Multi-Domain Object Detection Benchmark
- The Markovian Price of Information
- Selecting Computations: Theory and Applications
- Descending Price Optimally Coordinates Search
- Cost-Sensitive Freeze-thaw Bayesian Optimization for Efficient Hyperparameter Tuning
- Freeze-Thaw Bayesian Optimization
- Regret-Based (epsilon, delta) -optimal Stopping Criteria for Bayesian Optimization
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