Gradient vs Jacobian vs Hessian: one chart connects calculus to ML
burny_tech · x · 2026-11-14
A Matharium infographic systematically compares the gradient (first-order direction for gradient descent), the Jacobian (best linear approximation, used by backpropagation to propagate derivatives), and the Hessian (second-order curvature matrix powering Newton's method and critical-point classification), plus the Wronskian test for linear independence — e.g. sin x and cos x have Wronskian −1, making them independent solutions of y″+y=0.
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
- 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
- Google's Multi-Agent Systems Solve Open Problems in Math and Chemistry, Now External — pycui64 · 2026-11-14