Information Theory, Inference and Learning Algorithms
David J. C. MacKay
Information Geometry and Its Applications
Shun-Ichi Amari
Learning Theory From First Principles
Francis Bach
Elements of Programming Interviews: The Insiders' Guide
Adnan Aziz & Tsung-Hsien Lee & Amit Prakash
Non-Convex Optimization for Machine Learning
Prateek Jain & Purushottam Kar