When I finished a course learning elementary probability as a student majoring in computer science, I try to dive into machine learning theory. However, I find my knowledge acquring from the probability lesson is not enough.
Many occasions the machine learning theory deals with the conditional expectation and concentration inequalities(for example: Chernoff bound).And I find the conditional expectation and concentration inequalities related knowledge is especially important in machine learning(especially: law of total expectation).However, in my class, we covered none of these knowledge.
Also, few books on probability will mention these things. Can anyone recommand some resources(such as lecture notes, textbooks and so on) which deal with these things in detail? (My background is only with calculus 1 2 3 and linear algebra(our textbooks even without SVD) and elementary probability)
Concentration inequalities are hit or miss, but the below is a nice, non measure theoretic coverage of conditional expectation and probability in general (but at a much higher level than Intro to Probability):
https://faculty.math.illinois.edu/~r-ash/BPT/BPTCh4.pdf