I'm looking for references (books, papers, lecture notes etc) on generalization bounds and their proofs. Specifically, I'm looking to fully understand the technique of defining a hypothesis class (or distribution) and using a concentration inequality to obtain a generalization bound.
What are the standard references for such techniques?
For a concise overview the ideas you can read Mendelson's notes on the topic.
For a bit more check out the outline (and the links in it) by Kontorovich on how the basic and most fundamental bonds where proved.
For a more extended discussinon you can go over lecture notes of statistical learning courses. Here is one for example.
If books are your favorite kind of learning source, any good theoretic statistical learning book will have chapters discussing the basics. Here's links for two relevant books.
