Journal
SYNTHESE
Volume 199, Issue 3-4, Pages 9979-10015Publisher
SPRINGER
DOI: 10.1007/s11229-021-03233-1
Keywords
No-free-lunch theorems; Problem of induction; Machine learning
Categories
Ask authors/readers for more resources
The no-free-lunch theorems suggest that all machine learning algorithms lack justification, but in reality, many standard algorithms should be seen as model-dependent and can provide a model-relative justification.
The no-free-lunch theorems promote a skeptical conclusion that all possible machine learning algorithms equally lack justification. But how could this leave room for a learning theory, that shows that some algorithms are better than others? Drawing parallels to the philosophy of induction, we point out that the no-free-lunch results presuppose a conception of learning algorithms as purely data-driven. On this conception, every algorithm must have an inherent inductive bias, that wants justification. We argue that many standard learning algorithms should rather be understood as model-dependent: in each application they also require for input a model, representing a bias. Generic algorithms themselves, they can be given a model-relative justification.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available