Google DeepMind's 'The Elements of Differentiable Programming' book now readable in browser
mblondel_ml · x · 2026-10-23
Mathieu Blondel and Vincent Roulet of Google DeepMind have made their book "The Elements of Differentiable Programming" readable directly in the browser, with a PDF on arXiv and source code available. The book covers differentiation fundamentals, differentiable programs (control flows, data structures), differentiating through programs (autodiff, second-order methods, optimization and integration), smoothing, and first/second-order optimization plus duality — a comprehensive free textbook on differentiable programming.
More from Research
- VerifierBench: 222 Tasks Expose How Unreliable Agent-Generated Verifiers Are — Jianing Yin · 2026-10-23
- LM2LM: Frozen World Model Provides Scalable RL Rewards for AI Self-Improvement — Minhua Lin · 2026-10-23
- Stanford prof: LLM-fused models need radically new evals to separate memory from reasoning — anshulkundaje · 2026-10-23
- Stanford professor warns fused LLMs blur the line between memorization and real reasoning — anshulkundaje · 2026-10-23
- NSF picks nine teams for up to $3.5M each to boost super intelligence infrastructure efficiency — sh_reya · 2026-10-23
- CMU professor wins NSF-STRIDE AI Efficiency Challenge grant, hiring PhD students and postdocs — sh_reya · 2026-10-23