When can we treat certain experimental parameters as free variables? Consider trying to figure out whether or not a certain drug is efficacious. We design an experiment that proceeds as follow: Break a collection of experimental subjects up into two groups randomly.To one of the groups give the drug, and to the other give a… Continue reading Paper Review: Free Variables and Local Causality
Paper Review: Bayes, Bounds, and Rational Analysis
Bayesian learning and decision theory (arguably) characterize rationality for idealized agents. However, carrying out Bayesian calculations can often be costly. In particular, the kind of agent one is--whether a human, lizard, or computer--constrains the kind of information processing one can do. This gestures towards a question: what is the relationship between idealized rationality and rationality… Continue reading Paper Review: Bayes, Bounds, and Rational Analysis
Paper Review: Learnability can be undecideable
"Learnability can be undecideable" argues that the current mathematical frameworks we use to understand learnability are deeply flawed. It has been making big waves in the machine learning community, due to its rather spicy thesis. Thus, I figured it would be a good paper for me to review, and to explain its argument and implications.… Continue reading Paper Review: Learnability can be undecideable
The Crow's Nest 