365体育亚洲唯一官网入口-首頁(歡迎您)

合作交流
来访专家报告
浙江大学李松教授报告通知
发布人:蔡易  发布时间:2022-05-17   浏览次数:267

报告人:李松教授

报告题目:Low Rank Matrix Recovery with Adversarial Sparse Noise

报告摘要:

1Many problems in data science can be treated as recovering a low-rank matrix from a small number of random linear measurements, possibly corrupted with adversarial noise and dense noise. Recently, a bunch of theories on variants of models have been developed for different noises, but with fewer theories on the adversarial noise. In this talkwe study low-rank matrix recovery problem from linear measurements perturbed by l_1-bounded noise and sparse noise that can arbitrarily change an adversarially chosen ω-fraction of the measurement vector.

2For Gaussian measurements with nearly optimal number of measurements, we show that the nuclear-norm constrained least absolute deviation (LAD) can successfully estimate the ground-truthmatrix for any ω < 0.239. Similar robust recovery results are also established for an iterative hard thresholding algorithm applied to the rank-constrained LAD considering geometrically decaying step-sizes, and the unconstrained LAD based on matrix factorization as well as its subgradient descent solver.

报告时间:2022521日,上午900——12:00

报告形式:腾讯会议;会议号:299 494 443

报告人简介:李松,浙江大学求是特聘教授,钱江特聘专家,主要从事压缩感知、小波分析理论及其应用、采样理论以及相位恢复等理论研究工作,主持了国家自然科学基金重点项目、面上项目以及浙江省重大科技专项等基金项目,作为第一完成人获得教育部自然科学二等奖。