mlsanityData to 14 Oct 2026

Distributionally robust minimization in meta-learning for system identification

arXiv 2506.18074 ↗First posted 22 Jun 2025cs.LG cs.AI cs.SYcited by 3

Not on the map. Why?

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.

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

11 of 26 references.

References · 11

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2020Meta-Learning in Neural Networks: A Surveycited by 950
  3. 2022General-Purpose In-Context Learning by Meta-Learning Transformerscited by 105
  4. 2019Distributionally Robust Optimization: A Reviewcited by 76
  5. 2023How Smooth Is Attention?cited by 44
  6. 2023LipsFormer: Introducing Lipschitz Continuity to Vision Transformerscited by 34
  7. 2023From system models to class models: An in-context learning paradigmcited by 16
  8. 2022Meta-Learning of Neural State-Space Models Using Data From Similar Systemscited by 12
  9. 2023A Simple Yet Effective Strategy to Robustify the Meta Learning Paradigmcited by 10
  10. 2022Active Learning for Regression by Inverse Distance Weightingcited by 9
  11. 2024Enhanced Transformer architecture for in-context learning of dynamical systemscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Diffusion Sequence Models for Generative In-Context Meta-Learning of Robot Dynamicscited by 0
  2. 2026Variational meta-learning inference for low dimensional neural system identificationcited by 0
  3. 2026In-Context Learning for System Identification: Probabilistic Formulation, Long-Sequence Handling, and Benchmark Validationcited by 0