LiBOG: Lifelong Learning for Black-Box Optimizer Generation

TL;DR

LiBOG introduces a lifelong learning framework for Meta-Black-Box Optimization, enabling continuous adaptation to new problems and improved optimizer generation without catastrophic forgetting.

Contribution

This work presents LiBOG, the first lifelong learning approach for MetaBBO that consolidates knowledge across tasks to adaptively generate optimizers for evolving problem distributions.

Findings

LiBOG effectively mitigates catastrophic forgetting in lifelong learning.

LiBOG outperforms existing methods in generating high-performance optimizers.

LiBOG maintains adaptability to new problems while retaining past knowledge.

Abstract

Meta-Black-Box Optimization (MetaBBO) garners attention due to its success in automating the configuration and generation of black-box optimizers, significantly reducing the human effort required for optimizer design and discovering optimizers with higher performance than classic human-designed optimizers. However, existing MetaBBO methods conduct one-off training under the assumption that a stationary problem distribution with extensive and representative training problem samples is pre-available. This assumption is often impractical in real-world scenarios, where diverse problems following shifting distribution continually arise. Consequently, there is a pressing need for methods that can continuously learn from new problems encountered on-the-fly and progressively enhance their capabilities. In this work, we explore a novel paradigm of lifelong learning in MetaBBO and introduce LiBOG, a novel approach designed to learn from sequentially encountered problems and generate high-performance optimizers for Black-Box Optimization (BBO). LiBOG consolidates knowledge both across tasks and within tasks to mitigate catastrophic forgetting. Extensive experiments demonstrate LiBOG's effectiveness in learning to generate high-performance optimizers in a lifelong learning manner, addressing catastrophic forgetting while maintaining plasticity to learn new tasks.