# Learning to Optimize in Swarms

arXiv: https://arxiv.org/abs/1911.03787 · HTML: https://mlsanity.com/paper/1911.03787/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Nov 2019.

## Built on by (most cited first, 23 of 23)

- [Learning to Optimize: A Primer and A Benchmark](https://mlsanity.com/paper/2103.12828/) (2021)
- [VeLO: Training Versatile Learned Optimizers by Scaling Up](https://mlsanity.com/paper/2211.09760/) (2022)
- [Algorithm Evolution Using Large Language Model](https://mlsanity.com/paper/2311.15249/) (2023)
- [Bootstrapped Meta-Learning](https://mlsanity.com/paper/2109.04504/) (2021)
- [Practical tradeoffs between memory, compute, and performance in learned optimizers](https://mlsanity.com/paper/2203.11860/) (2022)
- [Symbol: Generating Flexible Black-Box Optimizers through Symbolic Equation Learning](https://mlsanity.com/paper/2402.02355/) (2024)
- [Symbolic Learning to Optimize: Towards Interpretability and Scalability](https://mlsanity.com/paper/2203.06578/) (2022)
- [B2Opt: Learning to Optimize Black-box Optimization with Little Budget](https://mlsanity.com/paper/2304.11787/) (2023)
- [Meta Learning Black-Box Population-Based Optimizers](https://mlsanity.com/paper/2103.03526/) (2021)
- [DRED: Zero-Shot Transfer in Reinforcement Learning via Data-Regularised Environment Design](https://mlsanity.com/paper/2402.03479/) (2024)
- [Towards Multi-Agent Reinforcement Learning driven Over-The-Counter Market Simulations](https://mlsanity.com/paper/2210.07184/) (2022)
- [Mnemosyne: Learning to Train Transformers with Transformers](https://mlsanity.com/paper/2302.01128/) (2023)
- [Learning to Generalize Provably in Learning to Optimize](https://mlsanity.com/paper/2302.11085/) (2023)
- [Stochastic Unrolled Federated Learning](https://mlsanity.com/paper/2305.15371/) (2023)
- [Learning for Robust Combinatorial Optimization: Algorithm and Application](https://mlsanity.com/paper/2112.10377/) (2021)
- [Learning Proximal Operators to Discover Multiple Optima](https://mlsanity.com/paper/2201.11945/) (2022)
- [M-L2O: Towards Generalizable Learning-to-Optimize by Test-Time Fast Self-Adaptation](https://mlsanity.com/paper/2303.00039/) (2023)
- [ModelPred: A Framework for Predicting Trained Model from Training Data](https://mlsanity.com/paper/2111.12545/) (2021)
- [Optimizer Amalgamation](https://mlsanity.com/paper/2203.06474/) (2022)
- [Learning Evolution via Optimization Knowledge Adaptation](https://mlsanity.com/paper/2501.02200/) (2025)
- [Make Optimization Once and for All with Fine-grained Guidance](https://mlsanity.com/paper/2503.11462/) (2025)
- [MACS: Multi-Agent Reinforcement Learning for Optimization of Crystal Structures](https://mlsanity.com/paper/2506.04195/) (2025)
- [POP: Prior-Fitted First-Order Optimization Policies](https://mlsanity.com/paper/2602.15473/) (2026)

## Abstract (arXiv)

Learning to optimize has emerged as a powerful framework for various optimization and machine learning tasks. Current such "meta-optimizers" often learn in the space of continuous optimization algorithms that are point-based and uncertainty-unaware. To overcome the limitations, we propose a meta-optimizer that learns in the algorithmic space of both point-based and population-based optimization algorithms. The meta-optimizer targets at a meta-loss function consisting of both cumulative regret and entropy. Specifically, we learn and interpret the update formula through a population of LSTMs embedded with sample- and feature-level attentions. Meanwhile, we estimate the posterior directly over the global optimum and use an uncertainty measure to help guide the learning process. Empirical results over non-convex test functions and the protein-docking application demonstrate that this new meta-optimizer outperforms existing competitors.