mlsanityData to 7 Oct 2026

Learning soft interventions in complex equilibrium systems

arXiv 2112.05729 ↗First posted 10 Dec 2021cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Complex systems often contain feedback loops that can be described as cyclic causal models. Intervening in such systems may lead to counterintuitive effects, which cannot be inferred directly from the graph structure. After establishing a framework for differentiable soft interventions based on Lie groups, we take advantage of modern automatic differentiation techniques and their application to implicit functions in order to optimize interventions in cyclic causal models. We illustrate the use of this framework by investigating scenarios of transition to sustainable economies.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 14 of its 42 references that are in the map. First posted on arXiv 10 Dec 2021.

Builds on

14 of 42 references.

References · 14

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2019Deep Equilibrium Modelscited by 603
  3. 2018Differentiable MPC for End-to-end Planning and Controlcited by 178
  4. 2016Foundations of Structural Causal Models with Cycles and Latent Variablescited by 134
  5. 2019Implicit Deep Learningcited by 124
  6. 2014From Ordinary Differential Equations to Structural Causal Models: the deterministic casecited by 41
  7. 2020Experimental Design in Two-Sided Platforms: An Analysis of Biascited by 39
  8. 2015backShift: Learning causal cyclic graphs from unknown shift interventionscited by 37
  9. 2020Causal models for dynamical systemscited by 34
  10. 2017Group invariance principles for causal generative modelscited by 20
  11. 2020A theory of independent mechanisms for extrapolation in generative modelscited by 17
  12. 2020Learning Game-Theoretic Models of Multiagent Trajectories Using Implicit Layerscited by 13
2 more
  1. 2020Conditional independences and causal relations implied by sets of equationscited by 5
  2. 2021Causality and independence in perfectly adapted dynamical systemscited by 4

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1.

2 papers.

  1. 2023Targeted Reduction of Causal Modelscited by 15
  2. 2022Fail-Safe Adversarial Generative Imitation Learningcited by 2