Corpus ID: 7133251

On causally asymmetric versions of Occam's Razor and their relation to thermodynamics

@article{Janzing2007OnCA,
  title={On causally asymmetric versions of Occam's Razor and their relation to thermodynamics},
  author={D. Janzing},
  journal={arXiv: Statistical Mechanics},
  year={2007}
}
  • D. Janzing
  • Published 2007
  • Mathematics, Physics
  • arXiv: Statistical Mechanics
In real-life statistical data, it seems that conditional probabilities for the effect given their causes tend to be less complex and smoother than conditionals for causes, given their effects. We have recently proposed and tested methods for causal inference in machine learning using a formalization of this principle. Here we try to provide some theoretical justification for causal inference methods based upon such a ``causally asymmetric'' interpretation of Occam's Razor. To this end, we… Expand

Figures from this paper

The Cause-Effect Problem: Motivation, Ideas, and Popular Misconceptions
  • D. Janzing
  • Computer Science
  • Cause Effect Pairs in Machine Learning
  • 2019
Causal Inference Using the Algorithmic Markov Condition
Distinguishing Cause and Effect via Second Order Exponential Models
Lecture 24, Causal Discovery
  • 2011
Detecting the direction of causal time series
Comparative Analysis of Viterbi Training and Maximum Likelihood Estimation for HMMs
...
1
2
...

References

SHOWING 1-10 OF 65 REFERENCES
Causal reasoning by evaluating the complexity of conditional densities with kernel methods
How the Laws of Physics Lie.
Causal Inference by Choosing Graphs with Most Plausible Markov Kernels
A Bayesian Approach to Causal Discovery
Causal Inference Using Nonnormality
...
1
2
3
4
5
...