报告题目：Guaranteed Tensor Recovery Fused Low-rankness and Smoothness

报 告 人：王海林 西安交通大学

邀请人：贾西西

报告时间：2022年12月7日（周三）10:00-11:30

腾讯会议ID：879-281-213

报告人简介：王海林，西安交通大学伟德国际BETVlCTOR博士，研究方向为张量稀疏性、机器学习。研究工作在TIP，TNNLS，AAAI等杂志和期刊发表。

报告摘要：Recent researches have made a significant progress by adopting two insightful tensor priors, including global low-rankness (L) and local smoothness (S) across different tensor modes, and encoding them as a sum of two separate regularization terms into the recovery model. However, unlike the primary theoretical developments on low-rank tensor recovery, these joint“L+S”models have no theoretical exact-recovery guarantees yet, making the methods lack reliability in real practice. To this crucial issue, in this work we build a unique regularization term, which essentially encodes both L and S priors of a tensor simultaneously. Especially, by equiping this single regularizer into the recovery models, we can rigorously prove the exact recovery guarantees for two typical tensor recovery tasks, i.e., tensor completion (TC) and tensor robust principal component analysis (TRPCA). To the best of our knowledge, this should be the first exact-recovery results among all related“L+S”methods for tensor recovery.

主办单位：伟德国际BETVlCTOR