应pc加拿大预测准确率李朋副教授邀请, 浙江大学数据科学研 究中心林俊宏研究员, 将于2022年11月23号(星期三)下午15:00在线举办学术报告.

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

腾讯会议号：557-737-425

报告摘要：Many problems in data science can be treated as recovering a low-rank matrix from a small number of random linear measurements, possibly corruptedwith 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 paper, we study low-rank matrix recovery problem from linear measurements perturbed by L1-bounded noise and sparse noise that can arbitrarily change an adversarially chosen w-fraction of the measurement vector. For Gaussian measurements withnearly optimal number of measurements, we show that the nuclear-norm constrained least absolute deviation (LAD) can successfully estimate the ground-truth matrix for any w < 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. This is a joint work with Prof. Song Li and Dr. Hang Xu.

报告人简介林俊宏，浙江大学“百人计划”研究员、博士生导师. 浙江大学数学系博士(导师: 李松教授); 香港城市大学数学系、意大利理工学院、瑞士洛桑联邦理工大学电子工程系博士后、研究员. 主要研究方向为压缩感知理论、学习理论、数据科学中的应用数学方法. 已在Applied and Computational Harmonic Analysis、Inverse Problems、Journal of Machine Learning Research、IEEE Transactions on Information Theory、IEEE Transactions on Signal Processing、International Conferenceon Machine Learning、Neural Information Processing Systems等期刊/会议上发表论文数篇. 受邀担任AAAI、ICML、IJCAI、NeurIPS、UAI等著名会议的PC members和多个重要期刊的评审专家. 共承担各类项目多项，包括：主持国家自然科学基金项目两项、参与三项; 参与国家重点研发计划项目等. 入选国家级青年人才计划、省级人才计划. 详情见其主页https://person.zju.edu.cn/junhong/

甘肃应用数学中心

甘肃省高校应用数学与复杂系统省级重点实验室

萃英学院

pc加拿大预测准确率

2022年11月17日