Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 20, 2025

LiBOG: Lifelong Learning for Black-Box Optimizer Generation

View Full Paper
Ask AI
Bookmark
Share

Authors

JPJiyuan PeiYMYi MeiJLJialin Liu

Discussion

Loading...

Member takes

Overview

Exploration of lifelong learning enhances optimization performance in diverse tasks, addressing challenges of catastrophic forgetting.

Key Points

  • LiBOG effectively learns from sequentially encountered problems, leading to high-performance optimizer generation.
  • Experiments show substantial improvements in optimizer performance compared to traditional methods, addressing common challenges.
  • Continuous learning enables adaptability to new tasks, ensuring resilience to catastrophic forgetting effects.
  • The study introduces a novel methodology for consolidating knowledge across and within tasks for improved outcomes.

Cite This Study

Pei et al. (2025) studied this question.

synapsesocial.com/papers/68d46aa631b076d99fa6728ehttps://doi.org/10.24963/ijcai.2025/991
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Reinforced In-Context Black-Box Optimization2024 · 1 citations
  2. 2Reinforced In-Context Black-Box Optimization2025 · 1 citations
  3. 3Machine Learning Algorithms for Improving Black Box Optimization Solvers2025
  4. 4Instance Generation for Meta-Black-Box Optimization through Latent Space Reverse Engineering2025
  5. 5Learning Low-Dimensional Embeddings for Black-Box Optimization2025