Algorithmic independence of initial condition and dynamical law in thermodynamics and causal inference
By Dominik Janzing, Rafael Chaves, B. Schoelkopf. 2015
37 citations recorded by the source corpus.
We postulate a principle stating that the initial condition of a physical system is typically algorithmically independent of the dynamical law. We discuss the implications of this principle and argue that they link thermodynamics and causal inference. On the one hand, they entail behavior that is similar to the usual arrow of time. On the other hand, they motivate a statistical asymmetry between cause and effect that has recently been postulated in the field of causal inference, namely, that the probability distribution P cause contains no information about the conditional distribution P effect ∣ cause and vice versa, while P effect may contain information about P cause ∣ effect .
Subfields: Cognitive Neuroscience, Experimental and Cognitive Psychology, History and Philosophy of Science, Causal Inference & Discovery
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Cognitive Neuroscience
- Nan Rosemary Ke
- Anirudh Goyal
- Stefan Bauer
- Yoshua Bengio
- Bernhard Schölkopf
- Nal Kalchbrenner
- Dominik Janzing
In Experimental and Cognitive Psychology
- Nan Rosemary Ke
- Stefan Bauer
- Bernhard Schölkopf
- Yoshua Bengio
- Anirudh Goyal
- Nal Kalchbrenner
- Francesco Locatello
In History and Philosophy of Science
In Causal Inference & Discovery
- Yoshua Bengio
- Anirudh Goyal
- Stefan Bauer
- Francesco Locatello
- Nan Rosemary Ke
- Nal Kalchbrenner
- Bernhard Schölkopf
- Dominik Janzing
Citations in the corpus
- Toward Causal Representation Learning (2021, methodology): “The algorithmic information theory provides a nat-ural framework for nonstatistical graphical models [120], [124].”
- Towards Causal Representation Learning (2021, neutral): “for non-statistical graphical models [120, 126].”
- Causality for Machine Learning (2019, background): “The assumption of algorithmically independent mechanisms has intriguing implications for physics, as it turns out to imply the second law of thermodynamics (i.e., the arrow of time) (Janzing et al., 2016).”