2 problems

For each fixed rational $p\in(1,\infty)$, given vectors $v_1,\ldots,v_m\in\mathbb{Q}^d$ defining the zonotope $Z=\left\{\sum_{i=1}^m\lambda_i v_i: -1\leq\lambda_i\leq 1\right\}$, d…

Consider a random depth $L$ neural network with input dimension $n_0$, hidden layer widths … output dimension $n_{L+1}$ and non-linearity $\sigma$. Suppose that the network is tune…