Corpus ID: 3333755

Learning Independent Causal Mechanisms

@inproceedings{Parascandolo2018LearningIC,
  title={Learning Independent Causal Mechanisms},
  author={Giambattista Parascandolo and Mateo Rojas-Carulla and Niki Kilbertus and B. Sch{\"o}lkopf},
  booktitle={ICML},
  year={2018}
}
Statistical learning relies upon data sampled from a distribution, and we usually do not care what actually generated it in the first place. From the point of view of causal modeling, the structure of each distribution is induced by physical mechanisms that give rise to dependences between observables. Mechanisms, however, can be meaningful autonomous modules of generative models that make sense beyond a particular entailed data distribution, lending themselves to transfer between problems. We… Expand
DISENTANGLE CAUSAL MECHANISMS
  • 2019
Competitive Training of Mixtures of Independent Deep Generative Models
Learning transferable representations
A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms
Spatially Structured Recurrent Modules
S2RMs: Spatially Structured Recurrent Modules
Independent mechanism analysis, a new concept?
Toward Causal Representation Learning
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 26 REFERENCES
Inferring deterministic causal relations
Generative Adversarial Nets
beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework
On causal and anticausal learning
Distinguishing Cause from Effect Based on Exogeneity
Expert Gate: Lifelong Learning with a Network of Experts
Causal Inference Using the Algorithmic Markov Condition
Auto-Encoding Variational Bayes
...
1
2
3
...