應(yīng)yl7703永利官網(wǎng)李朋副教授邀請(qǐng), 浙江大學(xué)數(shù)據(jù)科學(xué)研
究中心林俊宏研究員, 將于2022年11月23號(hào)(星期三)下午15:00在線舉辦學(xué)術(shù)報(bào)告.
報(bào)告題目：Low Rank Matrix Recovery with Adversarial Sparse Noise
騰訊會(huì)議號(hào)：557-737-425
報(bào)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.
報(bào)告人簡(jiǎn)介林俊宏，浙江大學(xué)“百人計(jì)劃”研究員、博士生導(dǎo)師. 浙江大學(xué)數(shù)學(xué)系博士(導(dǎo)師: 李松教授); 香港城市大學(xué)數(shù)學(xué)系、意大利理工學(xué)院、瑞士洛桑聯(lián)邦理工大學(xué)電子工程系博士后、研究員. 主要研究方向?yàn)閴嚎s感知理論、學(xué)習(xí)理論、數(shù)據(jù)科學(xué)中的應(yīng)用數(shù)學(xué)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/會(huì)議上發(fā)表論文數(shù)篇. 受邀擔(dān)任AAAI、ICML、IJCAI、NeurIPS、UAI等著名會(huì)議的PC members和多個(gè)重要期刊的評(píng)審專家. 共承擔(dān)各類項(xiàng)目多項(xiàng)，包括：主持國(guó)家自然科學(xué)基金項(xiàng)目?jī)身?xiàng)、參與三項(xiàng); 參與國(guó)家重點(diǎn)研發(fā)計(jì)劃項(xiàng)目等. 入選國(guó)家級(jí)青年人才計(jì)劃、省級(jí)人才計(jì)劃. 詳情見(jiàn)其主頁(yè)https://person.zju.edu.cn/junhong/
甘肅應(yīng)用數(shù)學(xué)中心
甘肅省高校應(yīng)用數(shù)學(xué)與復(fù)雜系統(tǒng)省級(jí)重點(diǎn)實(shí)驗(yàn)室
萃英學(xué)院
yl7703永利官網(wǎng)
2022年11月17日
