We develop an accelerated stochastic method for convex $(H_0,H_1)$-smooth optimization under heavy-tailed noise. The unbiased oracle has a finite $p$-th noise moment, $1<p\le2$, with constant, gradient-dependent, and gap-dependent terms. Our method combines accelerated updates with clipping, projection, and phase resta...
A. Lobanov, D. Dvinskikh, A. Gasnikov· 0 citations
A two-phase accelerated method that achieves, with high probability, an accelerated optimization contribution and smooth-subclass-optimal statistical dependence on accuracy, up to logarithmic and generalized-smoothness factors.
D. Dvinskikh, A. Gasnikov, A. Lobanov et al.· 1 citation
The first accelerated full-gradient and coordinate guarantees for this convex class are provided, to the knowledge, and practical implementation recommendations are provided.
A. Lobanov· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.