CONTENTS

Exercise: Compute the First Adam Update by Hand

Prerequisites: Adam Optimizer

Problem

Let g1=4g_1=4, m0=v0=0m_0=v_0=0, α=0.1\alpha=0.1, β1=0.9\beta_1=0.9, β2=0.999\beta_2=0.999, and ϵ=0\epsilon=0. Compute m1m_1, v1v_1, m^1\hat m_1, v^1\hat v_1, and the parameter step.

Hint

Jump to the solution when you're ready.