Pretrained Optimization Model for Zero-Shot Black Box Optimization
This addresses the problem of unreliable zero-shot optimization for applications requiring robust performance without extensive tuning, though it appears incremental as it builds on existing pretraining and fine-tuning approaches.
The paper tackles zero-shot black-box optimization by proposing a Pretrained Optimization Model (POM) that leverages knowledge from diverse tasks, and it demonstrates that POM outperforms state-of-the-art methods on benchmarks like BBOB and robot control tasks, particularly for high-dimensional problems.
Zero-shot optimization involves optimizing a target task that was not seen during training, aiming to provide the optimal solution without or with minimal adjustments to the optimizer. It is crucial to ensure reliable and robust performance in various applications. Current optimizers often struggle with zero-shot optimization and require intricate hyperparameter tuning to adapt to new tasks. To address this, we propose a Pretrained Optimization Model (POM) that leverages knowledge gained from optimizing diverse tasks, offering efficient solutions to zero-shot optimization through direct application or fine-tuning with few-shot samples. Evaluation on the BBOB benchmark and two robot control tasks demonstrates that POM outperforms state-of-the-art black-box optimization methods, especially for high-dimensional tasks. Fine-tuning POM with a small number of samples and budget yields significant performance improvements. Moreover, POM demonstrates robust generalization across diverse task distributions, dimensions, population sizes, and optimization horizons. For code implementation, see https://github.com/ninja-wm/POM/.