ESPN: Extremely Sparse Pruned Networks

Understand

Deep neural networks are often highly overparameterized, prohibiting their use in compute-limited systems.

• However, a line of recent works has shown that the size of deep networks can be considerably reduced by identifying a subset of neuron indicators (or mask) that correspond to significant weights prior to training.
• We demonstrate that an simple iterative mask discovery method can achieve state-of-the-art compression of very deep networks.
• Our algorithm represents a hybrid approach between single shot network pruning methods (such as SNIP) with Lottery-Ticket type approaches.