Timezone: »

Robust Tensor Decomposition with Gross Corruption
Quanquan Gu · Huan Gui · Jiawei Han

Tue Dec 09 04:00 PM -- 08:59 PM (PST) @ Level 2, room 210D
In this paper, we study the statistical performance of robust tensor decomposition with gross corruption. The observations are noisy realization of the superposition of a low-rank tensor $\mathcal{W}^*$ and an entrywise sparse corruption tensor $\mathcal{V}^*$. Unlike conventional noise with bounded variance in previous convex tensor decomposition analysis, the magnitude of the gross corruption can be arbitrary large. We show that under certain conditions, the true low-rank tensor as well as the sparse corruption tensor can be recovered simultaneously. Our theory yields nonasymptotic Frobenius-norm estimation error bounds for each tensor separately. We show through numerical experiments that our theory can precisely predict the scaling behavior in practice.

Author Information

Quanquan Gu (UCLA)
Huan Gui (Facebook, Inc)
Jiawei Han (University of Illinois at Urbana-Champaign)

More from the Same Authors