Reading and interpreting: basics of Japanese literature research
10:00-12:15
Talk & Lecture
1
2889289
/english/2024/0311/c19936a2889289/page.psp
2024-03-11
/_upload/article/images/29/a9/784425ff4a1ca6f1fa71496e92aa/6bdbf066-aeea-4e24-bae5-0cd9b0bf2672_s.jpg
/_upload/article/images/29/a9/784425ff4a1ca6f1fa71496e92aa/6bdbf066-aeea-4e24-bae5-0cd9b0bf2672.jpg
Speaker: Tsuyoshi Namigata, professor, Kyushu UniversityTime: 10:00-12:15, March 12Venue: East 1A-504, Zijingang CampusAbstract: Tsuyoshi Namigata is a Professor of Modern Japanese Literature and Comparative Literature at the Graduate School of Social and Cultural Studies, Kyushu University, Japan. He was a visiting scholar at the Institute for Japanese Studies of Seoul National University, Korea, 2011-2012, and the Harvard-Yenching Institute, the United States, 2022-2023. He published his Ph.D. dissertation as a monograph of Ekkyo no Avangyarudo [Border-Crossings in the Japanese Avantgarde] in 2005, later translated into Korean in 2013. He is now trying to examine the historical meaning of Japanese literary modernism during wartime and write the regional history of literary modernism in East Asia.
Tsuyoshi Namigata is a Professor of Modern Japanese Literature and Comparative Literature at the Graduate School of Social and Cultural Studies, Kyushu University, Japan.
Tsuyoshi Namigata
2024-03-12 17:27:11
Zijingang Campus
Weak identification of long memory with implications for volatility modeling
14:00
Talk & Lecture
2
2887878
/english/2024/0311/c19936a2887878/page.psp
2024-03-11
/_upload/article/images/5b/43/f46f2f4b443592564173f86811f4/069cbfc6-b5a2-4603-8060-e843fc3ee016_s.jpg
/_upload/article/images/5b/43/f46f2f4b443592564173f86811f4/069cbfc6-b5a2-4603-8060-e843fc3ee016.jpg
Speaker Prof. YU Jun, University of MacauTime: 14:00, March 18Avenue: Room 530, School of Economics, Zijingang CampusAbstract: Professor Jun Yu is currently UMDF chair Professor of Finance and Economics at the University of Macau and Dean of the Faculty of Business Administration at the University of Macau. Professor Yu haspublished more than 90 papers. Many of these publications are in leading journals in finance and economics, including Review of Financial Studies, Journal of Econometrics, Management Science and International Economic Review. His articles for detecting the presence of asset pricebubbles and estimating their origination and termination dates have initiated a new area of research on the econometric analysis of bubbles infinancial assets and real estate. Professor Yu is an inaugural fellow of the Society of Financial Econometrics and also a fellow of the Journal of Econometrics. He serves as an Associate Editor of the Journal of Econometrics and Econometric Theory.
Professor Jun Yu is currently UMDF chair Professor of Finance andEconomics at the University of Macau and Dean of the Faculty of Business Administration at the University of Macau.
Jun Yu
2024-03-18 11:40:10
Zijingang Campus
A Burden Shared is a Burden Halved: A Fairness-Adjusted Approach to Classification
14:00
Talk & Lecture
3
2884705
/english/2024/0304/c19936a2884705/page.psp
2024-03-04
/_upload/article/images/e0/13/f4ff355c4d9ab5d6405978cf4d5b/5806f1d0-80cb-4d36-965c-761fea249cb0_s.jpg
/_upload/article/images/e0/13/f4ff355c4d9ab5d6405978cf4d5b/5806f1d0-80cb-4d36-965c-761fea249cb0.jpg
Speaker: Bradley Rava, Lecturer, University of SydneyTime: 14:00, March 15Venue: Room 1417, Administrative Building, Zijingang CampusAbstract: We investigate fairness in classification, where automated decisions are made for individuals from different protected groups. In high-consequence scenarios, decision errors can disproportionately affect certain protected groups, leading to unfair outcomes. To address this issue, we propose a fairness-adjusted selective inference (FASI) framework and develop data-driven algorithms that achieve statistical parity by controlling and equalizing the false selection rate (FSR) among protected groups. Our FASI algorithm operates by converting the outputs of black-box classifiers into R-values, which are both intuitive and computationally efficient. The selection rules based on R-values, which effectively mitigate disparate impacts on protected groups, are provably valid for FSR control in finite samples. We demonstrate the numerical performance of our approach through both simulated and real data.Bio: Brad Rava is a Lecturer in the discipline of Business Analytics at the University of Sydney's Business School. His research focuses on Empirical Bayes techniques, Fairness in Machine Learning, Statistical Machine Learning, and High Dimensional Statistics. Brad Rava’s research interests focus modern statistical methods for addressing pressing societal problems that arise from combining automated decision making with high-risk scenarios. To properly communicate uncertainty in these high-risk scenarios, Brad’s research has drawn upon Empirical Bayes techniques, Fairness in Machine Learning, Statistical Machine Learning, and High Dimensional Statistics.
We propose a fairness-adjusted selective inference (FASI) framework and develop data-driven algorithms that achieve statistical parity by controlling and equalizing the false selection rate (FSR) among protected groups.
Bradley Rava
2024-03-15 17:07:38
Zijingang Campus
Preconditioned Riemannian Gradient Descent for Low-Rank Matrix Recovery Problems
10:00
Talk & Lecture
4
2884699
/english/2024/0304/c19936a2884699/page.psp
2024-03-04
/_upload/article/images/f4/92/276ea02049138631511057fe8edd/a079ecf2-850f-4e3a-aedf-4666c69af6c7_s.jpg
/_upload/article/images/f4/92/276ea02049138631511057fe8edd/a079ecf2-850f-4e3a-aedf-4666c69af6c7.jpg
Speaker: Prof. Jianfeng CAI, Hong Kong University of Science and TechnologyTime: 10:00, March 11Venue: Room 1417, Administrative Building, Zijingang CampusAbstract: The challenge of recovering low-rank matrices from linear samples is a common issue in various fields, including machine learning, imaging, signal processing, and computer vision. Non-convex algorithms have proven to be highly effective and efficient for low-rank matrix recovery, providing theoretical guarantees despite the potential for local minima. This talk presents a unifying framework for non-convex low-rank matrix recovery algorithms using Riemannian gradient descent. We demonstrate that numerous well-known non-convex low-rank matrix recovery algorithms can be considered special instances of Riemannian gradient descent, employing distinct Riemannian metrics and retraction operators. Consequently, we can pinpoint the optimal metrics and develop the most efficient non-convex algorithms. To illustrate this, we introduce a new preconditioned Riemannian gradient descent algorithm, which accelerates matrix completion tasks by more than ten times compared to traditional methods.
This talk presents a unifying framework for non-convex low-rank matrix recovery algorithms using Riemannian gradient descent.
Jianfeng CAI
2024-03-11 16:44:19
Zijingang Campus
Statistical inference for high-dimensional regression with proxy data
14:00
Talk & Lecture
5
2884643
/english/2024/0304/c19936a2884643/page.psp
2024-03-04
/_upload/article/images/5b/fc/84aa5d794bdca8ccdb6e424d631c/3e54ff08-cf0f-4536-814c-1dabafd674fb_s.jpg
/_upload/article/images/5b/fc/84aa5d794bdca8ccdb6e424d631c/3e54ff08-cf0f-4536-814c-1dabafd674fb.jpg
Speaker: Associate professor LI Sai, Renmin University of ChinaTime: 14:00, March 8Venue: Room 1417, Administrative Building, Zijingang CampusAbstract: We study estimation and inference for high-dimensional linear models with two types of “proxy data”. The first type of proxies encompasses marginal statistics and sample covariance matrices computed from distinct sets of individuals. We develop a rate optimal method for estimation and inference for the regression coefficient vector and its linear functionals based on the proxy data. We show the intrinsic limitations in the proxy-data based inference: the minimax optimal rate for estimation is slower than that in the conventional case where individual data are observed. The second type of proxy data is differentially private data. We propose method for private estimation and inference in high-dimensional regression with FDR control.
We study estimation and inference for high-dimensional linear models with two types of “proxy data”.
LI Sai
2024-03-08 14:00:00
Zijingang Campus
Ricci flow and pinched curvature on noncompact manifold
16:15-17:15
Talk & Lecture
6
2881807
/english/2024/0228/c19936a2881807/page.psp
2024-02-28
/_upload/article/images/85/18/f93bbcae4c73854743754b1b6dfd/157f6e09-9876-41c3-914e-6bcf1ecd8bb6_s.jpg
/_upload/article/images/85/18/f93bbcae4c73854743754b1b6dfd/157f6e09-9876-41c3-914e-6bcf1ecd8bb6.jpg
Speaker: Prof. Man Chun LEE, The Chinese University of Hong KongTime: 16:15-17:15, Feb. 28Venue: Room 101, No.2 Building, Haina Complex Building 2, Zijingang CampusAbstract: In this talk, we will discuss some recent development of Ricci flow existence on complete noncompact manifolds. In particular, we will discuss applications on manifold with curvature pinching.
In this talk, we will discuss some recent development of Ricci flow existence on complete noncompact manifolds. In particular, we will discuss applications on manifold with curvature pinching.
Man Chun LEE
2024-02-28 10:11:43
Zijingang Campus
Serendipity in science: a story on O2 sensors and fibroblasts in vascular health and disease
10:30
Talk & Lecture
7
2881926
/english/2024/0228/c19936a2881926/page.psp
2024-02-27
/_upload/article/images/58/c4/af7aa6434f81af7c48c99ed41845/2186afb8-63bb-4b48-844c-4cdd457e7887_s.jpg
/_upload/article/images/58/c4/af7aa6434f81af7c48c99ed41845/2186afb8-63bb-4b48-844c-4cdd457e7887.jpg
Speaker: Judith Sluimer, Professor, Principle Investigator Experimental Vascular Pathology group, Maastricht UniversityVenue: Room 245, the College of Life Sciences, Zijingang Campus_Judith SluimerVenue_ Room 245, the
Judith Sluimer, Professor, Principle Investigator Experimental Vascular Pathology group, Maastricht University
Judith Sluimer
2024-02-28 15:41:39
Zijingang Campus
100 years of the Schur-Weyl Duality
10:00
Talk & Lecture
8
2859593
/english/2024/0116/c19936a2859593/page.psp
2024-01-16
/_upload/article/images/36/7b/98dbdce74c30acb6c9f054fa8ac7/a1327837-797b-4017-848e-467b00928fcf_s.png
/_upload/article/images/36/7b/98dbdce74c30acb6c9f054fa8ac7/a1327837-797b-4017-848e-467b00928fcf.png
Speaker: Prof. DU Jie (The University of New South Wales)Venue: Room 210, Building 2, Haina Court, Zijingang CampusNote: Please scan the QR code in the picture above to register.
I will discuss Schur-Weyl Duality's latest developments from its quantum version in late 80s to the affine/super analoques and its recent generalization to tvpes other than A via quantum symmetric pairs and i-quantum groups. I will also mention the contributions by three groups of Chinese mathematicians.
2024-01-27 10:00:00
Room 210, Building 2, Haina Court, Zijingang Campus
How to leverage your time and exposure in ZIBS to harness future opportunities
11:00-12:00
Talk & Lecture
9
2859427
/english/2024/0116/c19936a2859427/page.psp
2024-01-16
/_upload/article/images/bf/00/22a75d1f4351ac372f17adfa8329/d00444b1-da07-4f49-ab05-3bf60743d579_s.png
/_upload/article/images/bf/00/22a75d1f4351ac372f17adfa8329/d00444b1-da07-4f49-ab05-3bf60743d579.png
Speaker: Koh Chaik Ming, Senior Research Fellow at National University of Singapore, Adjunct Professor at Singapore Management University and Nanyang Technological University.Venue: Room 359, ZIBS Building, Haining CampusLanguage: BilingualNote: Please scan the QR code in the picture above to register.
Koh Chaik Ming, Senior Research Fellow at National University of Singapore, will deliver a lecture on how to leverage the time and exposure in ZIBS to harness future opportunities in ZIBS Caeer Talk series. Welcome to participate!
2024-01-16 11:00:00
Room 359, ZIBS Building, Haining Campus