When Stick Figure's six-year-old song shot up the charts, the band was thrilled. But its viral moment was spurred by unauthorized AI remixes. The California-based reggae band Stick Figure has been around for 20 years, eight albums, and countless hours on the road, but lead vocalist and guitarist Scott Woodruff has never seen a track take off like "Angels Above Me" did this past week. The six-year-old song hit number one on the iTunes sales charts in six different countries, including the United Kingdom, Austria, and Canada, skyrocketing "out of nowhere," according to Woodruff. Stick Figure has had plenty of thrilling milestones before, with albums repeatedly hitting number one in the reggae category, and hit singles amassing hundreds of millions of streams.

We give a faster algorithm for computing an approximate John ellipsoid around $n$ points in $d$ dimensions. The best known prior algorithms are based on repeatedly computing the leverage scores of the points and reweighting them by these scores (Cohen et al., 2019). We show that this algorithm can be substantially sped up by delaying the computation of high accuracy leverage scores by using sampling, and then later computing multiple batches of high accuracy leverage scores via fast rectangular matrix multiplication. We also give low-space streaming algorithms for John ellipsoids using similar ideas.

Some related lower bounds include the work of Backurs et al. [2017] that solving kernel Support V ector Machines (SVM), ridge regression, or Principal Component Analysis (PCA) problems to high accuracy or approximating kernel density estimates up to a constant factor for kernels with

Neural Information Processing Systems http://nips.cc/

First, we show the negativeresult that no strongly sublinear sized coresets existforlogisticregression.

Neural Information Processing Systems http://nips.cc/

Such complexities are prohibitive for scaling to large datasets.