A new Linear Time Bi-level ${\ell }_{1,\infty }$ projection ; Application to the sparsification of auto-encoders neural networks

Michel Barlaud, Guillaume Perez, Jean-Paul Marmorat

The ${\ell }_{1,\infty }$ norm is an efficient-structured projection, but the complexity of the best algorithm is, unfortunately, $\mathcal{O}(nm\log (nm))$ for a matrix $n\t…