Pretty soon I will be finishing up Understanding Machine Learning: From Theory to Algorithms by Shai Ben-David and Shai Shalev-Shwartz. I absolutely love the subject and want to learn more, the only issue is I'm having trouble finding a book that could come after this. Ultimately, my goal is to read papers in JMLR's COLT.

  1. Is there a book similar to "Understanding Machine Learning: From Theory to Algorithms" that would progress my knowledge further and would go well after reading UML?

  2. Is there any other materials (not a book) that could allow me to learn more or prepare me for reading a journal like the one mentioned above?

(Also, taking courses in this is not really an option, so this will be for self-study).

(Note that I have also asked this question here on TCS SE, but it was recommended I also ask here.)


Although I have only partially read (or not read at all) some of the following resources and some of these resources may not cover more advanced topics than the ones presented in the book you are reading, I think they can still be useful for your purposes, so I will share them with you.

I would also like to note that if you understand the contents of the book you are currently reading, you are probably already prepared for reading some (if not most of) the research papers you wish to read. Initially, you may find them a little bit too succinct and sometimes unclear or complex, but you need to get used to this format, so there's nothing stopping you from trying to read them and learn even more by doing this exercise.



Courses (videos)

Lecture notes


See also this list of resources https://kiranvodrahalli.github.io/links/#resources-notes-textbooks-monographs-classes-etc compiled by Kiran Vodrahalli.

| improve this answer | |
  • $\begingroup$ Thank you so much looks like a great list! I didn't know that computational learning theory was very similar to statistical learning theory. Great papers I actually read A theory of the learnable earlier this week. Lots to work through here, any other tips are appreciated as well. Additionally it would be nice to know about how far I am from being able to read and understand journals like COLT. $\endgroup$ – PMaynard Apr 17 at 18:23
  • $\begingroup$ @PMaynard I will keep updating this answer with more resources. The idea is to provide a comprehensible list of useful resources. Maybe, in the future, I will also provide a description of each of these resources and for what purposes they are more useful. $\endgroup$ – nbro Apr 17 at 18:28
  • $\begingroup$ @PMaynard Regarding the part of being able to read the COLT papers, I suggest you just pick 1-2 papers (e.g. from proceedings.mlr.press/v99), and try to read them. This will make you understand your level. In any case, you shouldn't expect to be able to understand them in one reading iteration. It may require more iterations. The more you read, the easier and the faster it will be to capture the concepts in those papers. $\endgroup$ – nbro Apr 17 at 18:28
  • 1
    $\begingroup$ @PMaynard Note that some papers are very specific to one topic. So, even if you have good knowledge of the basics and even certain advanced topics, you may not be able to understand those papers without having knowledge of those specific topics in those papers. This is perfectly normal. $\endgroup$ – nbro Apr 17 at 18:32
  • 1
    $\begingroup$ Thanks, once again. Someone else had the same suggestion as far as how to start reading COLT so it sounds like a great idea. Maybe also a good idea to focus in on an area I like, reading and understanding everything is probably not a very practical goal. $\endgroup$ – PMaynard Apr 17 at 18:34

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.