Gradient-Descent on The Standard Errorhttps://jongha-jeon-dev.github.io/standarderror/tags/gradient-descent/Recent content in Gradient-Descent on The Standard ErrorHugo -- 0.123.7en-gbThu, 03 Sep 2026 00:00:00 +0000Numerical Analysis 1: Your Learning Rate Is a Step Sizehttps://jongha-jeon-dev.github.io/standarderror/lectures/numerical-analysis-1-step-size/Thu, 03 Sep 2026 00:00:00 +0000https://jongha-jeon-dev.github.io/standarderror/lectures/numerical-analysis-1-step-size/Gradient descent is forward Euler on the gradient flow, so the learning rate is a discretisation step with a stability limit — exactly 2/λ_max on a quadratic, and on a network 2.04 times larger than that formula says, because the curvature moves to meet whatever step you chose.