A spectral algorithm estimates the mean of a heavy-tailed distribution with optimal sub-Gaussian error in O~(n^2 d) time, without semidefinite programming.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.ST 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Fast Spectral Algorithm for Mean Estimation with Sub-Gaussian Rates
A spectral algorithm estimates the mean of a heavy-tailed distribution with optimal sub-Gaussian error in O~(n^2 d) time, without semidefinite programming.