Reading list

Resources

Papers, books, and courses I've found genuinely useful, organized by the topics I write about, with a line on where each one helped. This is an opinionated selection, not a comprehensive list.

Last updated 30 October 2026

Mathematics & Deep Learning Foundations

Books

Mathematics of Machine Learning Tivadar Danka
My primary math reference. I use it by topic (linear algebra, calculus, probability), not cover to cover.
Understanding Deep Learning Simon J. D. Prince, 2023
Clear derivations, good figures, and free online. For deep learning concepts when the active work needs them.

Reinforcement Learning & LLM Alignment

Papers

Proximal Policy Optimization Algorithms Schulman et al., 2017
The foundational PPO paper. Read alongside my PPO deep dive.
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models Shao et al., 2024
Where group-relative policy optimization (GRPO) originated.
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization Liu et al., 2026
Normalizes each reward independently before combining, so multi-reward GRPO keeps its advantage signal. Covered in my GDPO article.
Deep Reinforcement Learning from Human Preferences Christiano et al., 2017
The original RLHF paper — essential context for understanding alignment.
Direct Preference Optimization: Your Language Model is Secretly a Reward Model Rafailov et al., 2023
DPO simplified alignment by removing the reward model. A must-read.

Books

Reinforcement Learning: An Introduction Sutton & Barto, 2018 · 2nd edition
The RL reference I return to. Chapters 1–6 are essential foundations.

Contextual Bandits & Personalization

Papers

A Contextual-Bandit Approach to Personalized News Article Recommendation Li et al. (LinUCB), 2010
The LinUCB paper that kicked off practical contextual bandits.
Thompson Sampling for Contextual Bandits with Linear Payoffs Agrawal & Goyal, 2013
Rigorous treatment of Thompson Sampling in the contextual setting.
An Introduction to Multi-Armed Bandits Slivkins, 2019 (monograph)
Comprehensive monograph — works as both a textbook and reference.

Books & Courses

Bandit Algorithms Lattimore & Szepesvári, 2020
The definitive textbook. Dense but rewarding if you want the full theory.

LLM Evaluation

Papers

RAGAS: Automated Evaluation of Retrieval Augmented Generation Es et al., 2023
Framework for RAG-specific metrics — faithfulness, relevance, context recall.
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena Zheng et al., 2023
Foundational work on using LLMs to evaluate LLMs.

Tools

RAGAS
An open-source framework for retrieval-augmented generation evaluation.
DeepEval
A testing framework for LLM applications with a pytest-style interface.
LangSmith
End-to-end tracing and eval. Useful if you're already in the LangChain ecosystem.

RAG & Retrieval Systems

Papers

Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks Lewis et al., 2020
The original RAG paper. Still the right starting point.
Retrieval-Augmented Generation for Large Language Models: A Survey Gao et al., 2023
Comprehensive survey of RAG architectures and techniques.

Tools

LlamaIndex
My go-to for RAG pipelines. Great abstractions for data connectors and indexing.
Elasticsearch
Hybrid search (BM25 + dense vectors) is underrated. Scales well.

ML Systems & Production

Books

Designing Machine Learning Systems Chip Huyen, 2022
The best overview of MLOps end-to-end. Covers data, training, deployment, monitoring.
Hands-On Large Language Models Alammar & Grootendorst, 2024
Practical patterns for shipping LLM applications.

Courses

Stanford CS329S: Machine Learning Systems Design Chip Huyen
Covers the full lifecycle from problem framing to production monitoring.
Full Stack Deep Learning Pieter Abbeel et al.
Practical. Fills the gap between "I trained a model" and "it's in production."