主講人：羅珊 上海交通大學(xué)長(zhǎng)聘副教授
時(shí)間：2022年11月24日19：00
地點(diǎn)：騰訊會(huì)議 828 322 384
舉辦單位：數(shù)理學(xué)院
主講人介紹：羅珊，新加坡國(guó)立大學(xué)統(tǒng)計(jì)學(xué)博士，密歇根大學(xué)生物統(tǒng)計(jì)系訪(fǎng)問(wèn)學(xué)者?，F(xiàn)為上海交通大學(xué)數(shù)學(xué)科學(xué)學(xué)院長(zhǎng)聘副教授，博士生導(dǎo)師。主要研究領(lǐng)域?yàn)楦呔S統(tǒng)計(jì)推斷中的模型選擇標(biāo)準(zhǔn)和變量選擇方法、函數(shù)型數(shù)據(jù)和高階數(shù)據(jù)分析等。科研成果主要發(fā)表在 JASA、Statistica Sinica、Journal of Multivariate Analysis、Computational Statistics and Data Analysis 等統(tǒng)計(jì)學(xué)期刊和機(jī)器學(xué)習(xí)頂會(huì)等。
內(nèi)容介紹：As a prevalent distributed learning paradigm, Federated Learning (FL) trains a global model on a massive amount of devices with infrequent communication. This paper investigates a class of composite optimization and statistical recovery problems in FL setting, whose loss function consists of a data-dependent smooth loss and a nonsmooth regularizer. Examples include sparse linear regression using Lasso, low-rank matrix recovery using nuclear norm regularization, etc. In the existing literature, federated composite optimization algorithms are designed only from an optimization perspective without any statistical guarantees. In addition, they do not consider commonly used (restricted) strong convexity in statistical recovery problems. We advance the frontiers of this problem from both optimization and statistical perspectives. From optimization upfront, we propose a new algorithm named Fast Federated Dual Averaging for strongly convex and smooth loss, which provably enjoys linear speedup and the result matches the best-known convergence rate without the regularizer. From statistical upfront, for restricted strongly convex and smooth loss, we design another algorithm, namely Multi-stage Federated Dual Averaging, and provide a high probability complexity bound with linear speedup up to statistical precision. Numerical experiments in both synthetic and real data demonstrate that our methods perform better than other baselines. To the best of our knowledge, this is the first work providing fast optimization algorithms and statistical optimality guarantees for composite problems in FL.