Pith. sign in

Symbolic Learning to Optimize: Towards Interpretability and Scalability

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

Recent studies on Learning to Optimize (L2O) suggest a promising path to automating and accelerating the optimization procedure for complicated tasks. Existing L2O models parameterize optimization rules by neural networks, and learn those numerical rules via meta-training. However, they face two common pitfalls: (1) scalability: the numerical rules represented by neural networks create extra memory overhead for applying L2O models, and limit their applicability to optimizing larger tasks; (2) interpretability: it is unclear what an L2O model has learned in its black-box optimization rule, nor is it straightforward to compare different L2O models in an explainable way. To avoid both pitfalls, this paper proves the concept that we can "kill two birds by one stone", by introducing the powerful tool of symbolic regression to L2O. In this paper, we establish a holistic symbolic representation and analysis framework for L2O, which yields a series of insights for learnable optimizers. Leveraging our findings, we further propose a lightweight L2O model that can be meta-trained on large-scale problems and outperformed human-designed and tuned optimizers. Our work is set to supply a brand-new perspective to L2O research. Codes are available at: https://github.com/VITA-Group/Symbolic-Learning-To-Optimize.

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

How Should We Meta-Learn Reinforcement Learning Algorithms?

cs.LG · 2025-07-23 · conditional · novelty 6.0

A systematic comparison of black-box evolution, neural and symbolic distillation, and LLM-based proposal for meta-learning RL algorithms yields practical recommendations: warm-started LLM proposal is sample-efficient, same-size distillation gives cheap generalization gains, and symbolic search…

citing papers explorer

Showing 1 of 1 citing paper.

  • How Should We Meta-Learn Reinforcement Learning Algorithms? cs.LG · 2025-07-23 · conditional · none · ref 84 · internal anchor

    A systematic comparison of black-box evolution, neural and symbolic distillation, and LLM-based proposal for meta-learning RL algorithms yields practical recommendations: warm-started LLM proposal is sample-efficient, same-size distillation gives cheap generalization gains, and symbolic search…