\\
            &\hspace{10mm}\textbf{if} \: t > 1                                                   \\
            &\hspace{15mm} \textbf{b}_t \leftarrow \mu \textbf{b}_{t-1} + (1-\tau) g_t           \\
            &\hspace{10mm}\textbf{else}                                                          \\
            &\hspace{15mm} \textbf{b}_t \leftarrow g_t                                           \\
            &\hspace{10mm}\textbf{if} \: \textit{nesterov}                                       \\
            &\hspace{15mm} g_t \leftarrow g_{t} + \mu \textbf{b}_t                             \\
            &\hspace{10mm}\textbf{else}                                                   \\[-1.ex]
            &\hspace{15mm} g_t  \leftarrow  \textbf{b}_t                                         \\
            &\hspace{5mm}\textbf{if} \: \textit{maximize}                                          \\
            &\hspace{10mm}\theta_t \leftarrow \theta_{t-1} + \gamma g_t                   \\[-1.ex]
            &\hspace{5mm}\textbf{else}                                                    \\[-1.ex]
            &\hspace{10mm}\theta_t \leftarrow \theta_{t-1} - \gamma g_t                   \\[-1.ex]
            &\rule{110mm}{0.4pt}                                                          \\[-1.ex]
            &\bf{return} \:  \theta_t                                                     \\[-1.ex]
            &\rule{110mm}{0.4pt}                                                          \\[-1.ex]
       \end{aligned}

    Nesterov momentum is based on the formula from
    `On the importance of initialization and momentum in deep learning`__.
    aÉ