Answers are grounded in this paper and cite their sources.
Given an order-|d| tensor |A ∈ Rn × n × … × n|, we present a simple, element-wise sparsification algorithm that zeroes out all sufficiently small elements of |A|, keeps all sufficiently large elements of |A| and retains some of the remaining elements with probabilities proportional to the square of their magnitudes. We analyze the approximation accuracy of the proposed algorithm using a powerful inequality that we derive. This inequality bounds the spectral norm of a random tensor and is of independent interest. As a result, we obtain novel bounds for the tensor sparsification problem.
No takes yet. Share an insight, caveat, or question.
Nguyen et al. (2015) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: