1/5 Finding a do-operator in a @DeepMind article is a tectonic progress that deserves welcoming blessing. The "delusions" treated in this article are endemic of "Evidential Decision Theory" which Causality (ch 4.1.1 ucla.in/38bmhnO)
summarizes in a mnemonic limerick:
summarizes in a mnemonic limerick:
https://twitter.com/GnomeSortingHat/status/1458690597724712961
2/5
- Whatever evidence an act might provide
- On what could have caused the act,
- Should never be used to help one decide
- On whether to choose that same act.
Typical real life ramifications of these delusions are:
(1) patients should avoid going to the doctor “to reduce the
- Whatever evidence an act might provide
- On what could have caused the act,
- Should never be used to help one decide
- On whether to choose that same act.
Typical real life ramifications of these delusions are:
(1) patients should avoid going to the doctor “to reduce the
3/5
probability that one is seriously ill”
(2) workers should never hurry to work, to reduce the probability of having overslept, and more.
The deployment of the do-operator eliminates these "delusions" and has led to the "sequential backdoor criterion" of Sec. 4.4.3.
probability that one is seriously ill”
(2) workers should never hurry to work, to reduce the probability of having overslept, and more.
The deployment of the do-operator eliminates these "delusions" and has led to the "sequential backdoor criterion" of Sec. 4.4.3.
4/5
Ortega etal are justified to title the paper "Shaking the Foundations", since even seasoned decision analysts often use the wrong probabilities on their decision trees (see Sec.11.6
ucla.in/2NnfGPQ#page=50)
not to mention ML researchers, many of whom still equate "knowledge"
Ortega etal are justified to title the paper "Shaking the Foundations", since even seasoned decision analysts often use the wrong probabilities on their decision trees (see Sec.11.6
ucla.in/2NnfGPQ#page=50)
not to mention ML researchers, many of whom still equate "knowledge"
5/5
with "training".
I haven't read the last part but would recommend that the authors take a good look at the "sequential backdoor criterion" to ensure that we do not introduce new "delusions" in trying to eliminate old ones.
#DataScience #MachineLearning #DeepLearning #AI
with "training".
I haven't read the last part but would recommend that the authors take a good look at the "sequential backdoor criterion" to ensure that we do not introduce new "delusions" in trying to eliminate old ones.
#DataScience #MachineLearning #DeepLearning #AI
• • •
Missing some Tweet in this thread? You can try to
force a refresh
