Corpus ID: 195699378

Approximate Causal Abstraction

@article{Beckers2019ApproximateCA,
  title={Approximate Causal Abstraction},
  author={Sander Beckers and F. Eberhardt and Joseph Y. Halpern},
  journal={Uncertainty in artificial intelligence : proceedings of the ... conference. Conference on Uncertainty in Artificial Intelligence},
  year={2019},
  volume={2019}
}
  • Sander Beckers, F. Eberhardt, Joseph Y. Halpern
  • Published 2019
  • Computer Science, Medicine
  • Uncertainty in artificial intelligence : proceedings of the ... conference. Conference on Uncertainty in Artificial Intelligence
  • Scientific models describe natural phenomena at different levels of abstraction. Abstract descriptions can provide the basis for interventions on the system and explanation of observed phenomena at a level of granularity that is coarser than the most fundamental account of the system. Beckers and Halpern (2019), building on work of Rubenstein et al. (2017), developed an account of abstraction for causal models that is exact. Here we extend this account to the more realistic case where an… CONTINUE READING
    A Bounded Model of the Communication Delay for System Integrity Protection Schemes
    19
    Causal Feature Learning for Utility-Maximizing Agents

    References

    Publications referenced by this paper.
    SHOWING 1-9 OF 9 REFERENCES
    New Vessels after Stroke: Postischemic Neovascularization and Regeneration
    70
    E V ects of age on sleep apnoea in men : I . Prevalence and severity
    • 1998
    [2] Recognition and identification of cyanobacteria
    124
    Abstracting Causal Models
    9
    Actual Causality
    91
    Unsupervised Discovery of El Nino Using Causal Feature Learning on Microlevel Climate Data
    10
    Causal Consistency of Structural Equation Models
    27
    Structural Intervention Distance (SID) for Evaluating Causal Graphs
    23
    Causal Inference of Ambiguous Manipulations
    39