# Distributionally robust minimization in meta-learning for system identification

arXiv: https://arxiv.org/abs/2506.18074 · HTML: https://mlsanity.com/paper/2506.18074/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 26 references that are in the map.
- First posted on arXiv 22 Jun 2025.

## Builds on (most cited first, 11 of 11)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Meta-Learning in Neural Networks: A Survey](https://mlsanity.com/paper/2004.05439/) (2020)
- [General-Purpose In-Context Learning by Meta-Learning Transformers](https://mlsanity.com/paper/2212.04458/) (2022)
- [Distributionally Robust Optimization: A Review](https://mlsanity.com/paper/1908.05659/) (2019)
- [How Smooth Is Attention?](https://mlsanity.com/paper/2312.14820/) (2023)
- [LipsFormer: Introducing Lipschitz Continuity to Vision Transformers](https://mlsanity.com/paper/2304.09856/) (2023)
- [From system models to class models: An in-context learning paradigm](https://mlsanity.com/paper/2308.13380/) (2023)
- [Meta-Learning of Neural State-Space Models Using Data From Similar Systems](https://mlsanity.com/paper/2211.07768/) (2022)
- [A Simple Yet Effective Strategy to Robustify the Meta Learning Paradigm](https://mlsanity.com/paper/2310.00708/) (2023)
- [Active Learning for Regression by Inverse Distance Weighting](https://mlsanity.com/paper/2204.07177/) (2022)
- [Enhanced Transformer architecture for in-context learning of dynamical systems](https://mlsanity.com/paper/2410.03291/) (2024)

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

- [Diffusion Sequence Models for Generative In-Context Meta-Learning of Robot Dynamics](https://mlsanity.com/paper/2604.13366/) (2026)
- [Variational meta-learning inference for low dimensional neural system identification](https://mlsanity.com/paper/2607.18965/) (2026)
- [In-Context Learning for System Identification: Probabilistic Formulation, Long-Sequence Handling, and Benchmark Validation](https://mlsanity.com/paper/2610.13411/) (2026)

## Abstract (arXiv)

Meta learning aims at learning how to solve tasks, and thus it allows to estimate models that can be quickly adapted to new scenarios. This work explores distributionally robust minimization in meta learning for system identification. Standard meta learning approaches optimize the expected loss, overlooking task variability. We use an alternative approach, adopting a distributionally robust optimization paradigm that prioritizes high-loss tasks, enhancing performance in worst-case scenarios. Evaluated on a meta model trained on a class of synthetic dynamical systems and tested in both in-distribution and out-of-distribution settings, the proposed approach allows to reduce failures in safety-critical applications.