The following books have been especially valuable in deepening my understanding of the theoretical foundations of machine learning problems. I keep them on hand as practical references, using them as toolkits when deriving bounds or revisiting key machine learning modeling techniques.

1. "Prediction, Learning, and Games" by Nicolò Cesa-Bianchi and Gábor Lugosi [Book]
2. "High-Dimensional Statistics: A Non-Asymptotic Viewpoint" by Martin J. Wainwright [Book]
3. "Foundations of Machine Learning (2nd edition)" by Mehryar Mohri, Afshin Rostamizadeh, and Ameet Talwalkar [Book]


Below is a short recommended reading list for PhD students, featuring resources that have had a lasting impact on me. These materials cover essential topics such as cultivating the right mindset for research, managing the inevitable frustrations that come with it, learning the art and craft of writing scientific papers, and delivering engaging presentations. I highly encourage graduate students aspiring to pursue academic careers to explore these resources.

Research
1. "You and Your Research" by Richard W. Hamming [Transcript]
2. "Statistical Modeling: The Two Cultures" by Leo Breiman [Article]

PhD Life
1. "A PhD Is Not Enough! A Guide to Survival in Science" by Peter J. Feibelman [Book]
2. "The Ph.D. Grind" by Philip J. Guo [Book]

Writing
1. "Writing Science: How to Write Papers That Get Cited and Proposals That Get Funded" by Joshua Schimel [Book]
2. "PhD: How to write a great research paper" by Simon Jones [Video]

Communication
1. "How to Give a Great Research Talk" by Simon Jones [Video]
2. "How to Email Your Professor" by Laura Portwood-Stacer [Article]

Note, all materials were found through Google searches; if any content infringes on copyright, kindly inform me and I will act immediately.