제목 [학술세미나] SEED 세미나 안내
작성일 2018-08-23 16:10:10
내용 SEED Seminar Announcement

We cordially invite you to attend the SEED seminar by XuDong Li (Princeton University ) on Thursday, 30 Aug 2018@4-5PM (UTC+8 note time difference).

* Title : Exploring the Second Order Sparsity in Large Scale Optimization
* Speaker : XuDong Li, Princeton University
* Time : 16:00-17:00 (Singapore), Thu, 30 Aug 2018
* Virtual seminar room : webconf.vc.dfn.de/optimization<http://webconf.vc.dfn.de/optimization>
* Room Passcode : seed
* NUS Venue : S16-05-98

* Abstract
In this talk, we shall demonstrate how the second order sparsity (SOS) in important optimization problems such as the sparse optimization models, semidefinite programming, and many others can be explored to induce efficient algorithms. The SOS property allows us to incorporate the semismooth Newton methods into the augmented Lagrangian method framework in a way that the subproblems involved only need low to medium costs, e.g., for lasso problems with sparse solutions, the costs for solving the subproblems at each iteration of our second order method are comparable or even lower than those in many first order methods. Consequently, with the fast convergence rate in hand, usually asymptotically superlinear linear, we now reach the stage of being able to solve many challenging large scale convex optimization problems efficiently and robustly. For the purpose of illustration, we present a highly efficient software called LassoNAL for solving the well-known Lasso-type problems.

The SEED seminar series is jointly organized by researchers from National University of Singapore, Zuse Institute Berlin, The Institute of Statistical Mathematics, Academia Sinica, University College London, Seoul National University and the Hong Kong University of Science and Technology. SEED stands for Statistics maschinElEarning Datascience. Motivated by the availability of big complex data and the fast development of new techniques in machine learning and data science, SEED aims to provide an online research platform for seminars focusing on important and timely interdisciplinary research topics on Statistics, Machine learning, Data Science, Mathematics, Operation Research, Computer Science, and Engineering. The online seminar series are co-hosted and organised by several research institutes in different countries. The mission is to exchange research ideas, educate young researchers, and promote international research and education collaborations.For more information, please visit the SEED website https://seed.stat.nus.edu.sg/index.php


Confirmed seminars will be given by the following researchers:

Speaker Title   Date and Time   Host
Hong Kong, Singapore and Taiwan (UTC +8)        Japan and Korea
(UTC +9)        Germany
(UTC +1)        U.K.
Hideitsu Hino<https://researchmap.jp/read0143154/?lang=english>
Current Dipole Localization from EEG with Birth-Death Process<https://seed.stat.nus.edu.sg/index.php/events#Hino>       Wed, 9 Jan 2019
16:00 - 17:00   Wed, 9 Jan 2019
17:00 - 18:00   Wed, 9 Jan 2019
09:00 - 10:00   Wed, 9 Jan 2019
08:00 - 09:00   ISM
Shuhei Mano<https://researchmap.jp/mano_shuhei/?lang=english>   
A Direct Sampler from Log-affine Models with Aid of Computational Algebra<https://seed.stat.nus.edu.sg/index.php/events#Mano>       Wed, 31 Oct 2018
16:00 - 17:00   Wed, 31 Oct 2018
17:00 - 18:00   Wed, 31 Oct 2018
09:00 - 10:00   Wed, 31 Oct 2019
08:00 - 09:00   ISM
Ostap Okhrin<https://www.researchgate.net/profile/Ostap_Okhrin> TBA<https://seed.stat.nus.edu.sg/index.php/events#Mano>       Fri, 28 Sep 2018
16:30 - 17:30   Fri, 28 Sep 2018
17:30 - 18:30   Fri, 28 Sep 2018
10:30 - 11:30   Fri, 28 Sep 2019
09:30 - 10:30   NUS
Xuan Leng<https://lengxuan.weebly.com/> Bias correction for the maximum likelihood estimator of the extreme value index<https://seed.stat.nus.edu.sg/index.php/events#Xuan>     Fri, 14 Sep 2018
15:00 - 16:00   Fri, 14 Sep 2018
16:00 - 17:00   Fri, 14 Sep 2018
09:00 - 10:00   Fri, 14 Sep 2019
08:00 - 09:00   NUS
파일 -