# LiBOG: Lifelong Learning for Black-Box Optimizer Generation

arXiv: https://arxiv.org/abs/2505.13025 · HTML: https://mlsanity.com/paper/2505.13025/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 42 references that are in the map.
- First posted on arXiv 19 May 2025.

## Builds on (most cited first, 20 of 20)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [Symbolic Discovery of Optimization Algorithms](https://mlsanity.com/paper/2302.06675/) (2023)
- [Towards Continual Reinforcement Learning: A Review and Perspectives](https://mlsanity.com/paper/2012.13490/) (2020)
- [Recent Advances in Bayesian Optimization](https://mlsanity.com/paper/2206.03301/) (2022)
- [Transient Non-Stationarity and Generalisation in Deep Reinforcement Learning](https://mlsanity.com/paper/2006.05826/) (2020)
- [Deep Reinforcement Learning Based Parameter Control in Differential Evolution](https://mlsanity.com/paper/1905.08006/) (2019)
- [MetaBox: A Benchmark Platform for Meta-Black-Box Optimization with Reinforcement Learning](https://mlsanity.com/paper/2310.08252/) (2023)
- [How Good Is Neural Combinatorial Optimization? A Systematic Evaluation on the Traveling Salesman Problem](https://mlsanity.com/paper/2209.10913/) (2022)
- [Symbol: Generating Flexible Black-Box Optimizers through Symbolic Equation Learning](https://mlsanity.com/paper/2402.02355/) (2024)
- [Meta-Learning for Black-box Optimization](https://mlsanity.com/paper/1907.06901/) (2019)
- [Improving Performance in Reinforcement Learning by Breaking Generalization in Neural Networks](https://mlsanity.com/paper/2003.07417/) (2020)
- [Symbolic Learning to Optimize: Towards Interpretability and Scalability](https://mlsanity.com/paper/2203.06578/) (2022)
- [Catastrophic Interference in Reinforcement Learning: A Solution Based on Context Division and Knowledge Distillation](https://mlsanity.com/paper/2109.00525/) (2021)
- [Optimizing Large-Scale Hyperparameters via Automated Learning Algorithm](https://mlsanity.com/paper/2102.09026/) (2021)
- [Meta Learning Black-Box Population-Based Optimizers](https://mlsanity.com/paper/2103.03526/) (2021)
- [Memory-efficient Reinforcement Learning with Value-based Knowledge Consolidation](https://mlsanity.com/paper/2205.10868/) (2022)
- [Learning from Offline and Online Experiences: A Hybrid Adaptive Operator Selection Framework](https://mlsanity.com/paper/2404.10252/) (2024)
- [PyHopper -- Hyperparameter optimization](https://mlsanity.com/paper/2210.04728/) (2022)

## Built on by (most cited first, 3 of 3)

- [DesignX: Human-Competitive Algorithm Designer for Black-Box Optimization](https://mlsanity.com/paper/2505.17866/) (2025)
- [Lifelong Learning with Behavior Consolidation for Vehicle Routing](https://mlsanity.com/paper/2509.21765/) (2025)
- [Keep Rehearsing and Refining: Lifelong Learning Vehicle Routing under Continually Drifting Tasks](https://mlsanity.com/paper/2601.22509/) (2026)

## Abstract (arXiv)

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.