Skip to yearly menu bar Skip to main content


Breaking the Heavy-Tailed Noise Barrier in Stochastic Optimization Problems

Nikita Puchkin · Eduard Gorbunov · Nickolay Kutuzov · Alexander Gasnikov

MR1 & MR2 - Number 167
[ ]
Fri 3 May 8 a.m. PDT — 8:30 a.m. PDT

Abstract: We consider stochastic optimization problems with heavy-tailed noise with structured density. For such problems, we show that it is possible to get faster rates of convergence than $O(K^{-2(\alpha - 1) / \alpha})$, when the stochastic gradients have finite $\alpha$-th moment, $\alpha \in (1, 2]$. In particular, our analysis allows the noise norm to have an unbounded expectation. To achieve these results, we stabilize stochastic gradients, using smoothed medians of means. We prove that the resulting estimates have negligible bias and controllable variance. This allows us to carefully incorporate them into clipped-SGD and clipped-SSTM and derive new high-probability complexity bounds in the considered setup.

Live content is unavailable. Log in and register to view live content