Learning the Positions in CountSketch

arXiv:2306.06611v2 Announce Type: replace
Abstract: We consider sketching algorithms which first compress data by multiplication with a random sketch matrix, and then apply the sketch to quickly solve an optimization problem, e.g., low-rank approximation and regression. In the learning-based sketching paradigm proposed by~\cite{indyk2019learning}, the sketch matrix is found by choosing a random sparse matrix, e.g., CountSketch, and then the values of its non-zero entries are updated by running gradient descent on a training data set. Despite the growing body of …

abstract algorithms apply approximation arxiv cs.ds cs.lg data found low matrix optimization paradigm random regression solve type