Meta Learning Black-Box Population-Based Optimizers
This work addresses the challenge of creating adaptive optimizers for specific problem classes, offering a novel meta-learning approach that could benefit researchers and practitioners in optimization and machine learning, though it appears incremental in building on existing meta-learning and POMDP concepts.
The paper tackled the problem of designing optimizers tailored to specific problems by proposing a meta-learning framework called LTO-POMDP, which uses deep recurrent neural networks to learn population-based black-box optimizers. The results showed that the learned optimizers achieved better generalization and higher sample efficiency than state-of-the-art generic algorithms like CMA-ES on various black-box optimization tasks and hyperparameter tuning.
The no free lunch theorem states that no model is better suited to every problem. A question that arises from this is how to design methods that propose optimizers tailored to specific problems achieving state-of-the-art performance. This paper addresses this issue by proposing the use of meta-learning to infer population-based black-box optimizers that can automatically adapt to specific classes of problems. We suggest a general modeling of population-based algorithms that result in Learning-to-Optimize POMDP (LTO-POMDP), a meta-learning framework based on a specific partially observable Markov decision process (POMDP). From that framework's formulation, we propose to parameterize the algorithm using deep recurrent neural networks and use a meta-loss function based on stochastic algorithms' performance to train efficient data-driven optimizers over several related optimization tasks. The learned optimizers' performance based on this implementation is assessed on various black-box optimization tasks and hyperparameter tuning of machine learning models. Our results revealed that the meta-loss function encourages a learned algorithm to alter its search behavior so that it can easily fit into a new context. Thus, it allows better generalization and higher sample efficiency than state-of-the-art generic optimization algorithms, such as the Covariance matrix adaptation evolution strategy (CMA-ES).