Textbooks on Various Subjects

I believe well-written textbooks (or even theses) are the fastest way to learn topics that have achieved critical mass. Inspired by a similarly titled post on LessWrong 2.0, I have my own evolving list.

For obvious reasons, I haven't read most books cover to cover. As I read more, I might start providing broader context towards - what can and should be read, what can be skipped, at what stage of the career to read it and so on, to make this list more meaningful. The years are only indicative and by all means prefer the latest edition/print (I've mentioned both first and latest prints).

General Math

Linear Algebra

Optimization

Bayesian Inference

Monte Carlo Methods

Information Theory

Stochastic Processes

Machine Learning / Statistics

Gaussian Processes

Deep Learning

  • โ€‹Deep Learning by Ian Goodfellow and Yoshua Bengio and Aaron Courville (2016)

Reinforcement Learning

Learning Theory

โ€‹