New policy-based method reduces black-box simulator calls by 10x

Researchers have developed a new method to optimize black-box simulators, which are often non-differentiable and computationally expensive. This approach involves learning a policy that guides the training of a differentiable surrogate model. The gradients from this surrogate are then used to optimize simulation parameters via SGD. This technique amortizes the cost of downstream optimization, requiring up to 10 times fewer simulator calls compared to existing methods like Bayesian optimization and numerical optimization. AI

IMPACT This method could significantly reduce the computational cost of training and optimizing complex simulation models, accelerating research and development across various scientific and engineering fields.

RANK_REASON The cluster contains an academic paper detailing a new methodology for black-box optimization. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• arXiv
• Hugging Face
• SGD
• Simulating, Fast and Slow: Learning Policies for Black-Box Optimization
• Tim Bakker

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →