MIT Press 496-page ML theory textbook 'Learning Theory from First Principles' is free
burny_tech · x · 2026-11-14
Free graduate-level ML theory textbook. Learning Theory from First Principles (MIT Press, 2024) is a rigorous 496-page textbook covering the mathematical foundations of machine learning:
- Statistical learning theory and optimization
- Neural networks, generalization, and overparameterized models
The shared pages show its treatment of underfitting/overfitting and empirical risk minimization. The PDF is freely available, making it an easy addition to any ML learner's library.
More from Research
- 18-year-old independent researcher shows self-repairing training converges, validated in 383 runs — Cohere · 2026-11-14
- AWS adds OpenFold3 to SageMaker JumpStart for private biomolecular structure prediction — AWS ML Blog · 2026-11-14
- ICML 2027 Caps Submissions at 20, Ties Authorship to Reviewing Duty — Gravitist · 2026-11-14
- Physicist corrects record: OpenAI's Lean proof shows Yang–Mills construction is interacting — danintheory · 2026-11-14
- Inkling 2 Small trained partly in NVFP4 with mixed-precision recipe — HanGuo97 · 2026-11-14
- New preprint: protein foundation models struggle with local chemistry, probed via NMR chemical shifts — anshulkundaje · 2026-11-14