# META-SMGO-Delta: similarity as a prior in black-box optimization

arXiv: https://arxiv.org/abs/2305.00438 · HTML: https://mlsanity.com/paper/2305.00438/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 24 references that are in the map.
- First posted on arXiv 30 Apr 2023.

## Builds on (most cited first, 8 of 8)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Meta-Learning: A Survey](https://mlsanity.com/paper/1810.03548/) (2018)
- [Control-oriented meta-learning](https://mlsanity.com/paper/2204.06716/) (2022)
- [Meta-Learning Priors for Safe Bayesian Optimization](https://mlsanity.com/paper/2210.00762/) (2022)
- [Meta Learning MPC using Finite-Dimensional Gaussian Process Approximations](https://mlsanity.com/paper/2008.05984/) (2020)
- [Imitation and Transfer Learning for LQG Control](https://mlsanity.com/paper/2303.09002/) (2023)
- [Optimizing Closed-Loop Performance with Data from Similar Systems: A Bayesian Meta-Learning Approach](https://mlsanity.com/paper/2211.00077/) (2022)
- [Data-driven control and transfer learning using neural canonical control structures*](https://mlsanity.com/paper/2302.04042/) (2023)

## Abstract (arXiv)

When solving global optimization problems in practice, one often ends up repeatedly solving problems that are similar to each others. By providing a rigorous definition of similarity, in this work we propose to incorporate the META-learning rationale into SMGO-Delta, a global optimization approach recently proposed in the literature, to exploit priors obtained from similar past experience to efficiently solve new (similar) problems. Through a benchmark numerical example we show the practical benefits of our META-extension of the baseline algorithm, while providing theoretical bounds on its performance.