1 problem

0 votes0 replies1 view
The optimal-rate lower-bound conjecture for least squares regression with heavy-tailed errors
Let $\mathcal{X}=[0,1]$ and let $P$ be a probability measure on $\mathcal{X}$ with Lebesgue density bounded away from $0$ and $\infty$ . Let $\xi_i$ be i.i.d. mean-zero errors indep…
Conjectureopenconvergence-rates heavy-tailed-errors least-squares-regressionarXiv posted 2 days ago

The optimal-rate lower-bound conjecture for least squares regression with heavy-tailed errors