Welcome to MINDS!

Established in 2020, POSTECH Mathematical Institute for Data Science (MINDS) is the community of researchers in the areas of fundamental data science, machine learning, artificial intelligence, scientific computing, and humanitarian data science. MINDS mission is to provide a platform for collaboration among researchers and to provide various opportunities for students in data science. MINDS also aims to use our data science research to serve our local and global communities pursuing humanitarian data science.


Upcoming Events



MINDS Seminar Series | Jakwang Kim (University of Wisconsin-Madison) - Adversarial robustness vie optimal transport theory

period : 2023-05-30 ~ 2023-05-30
time : 10:00:00 ~ 11:00:00
개최 장소 : Online streaming (Zoom)
Topic : Adversarial robustness vie optimal transport theory
Date 2023-05-30 ~ 2023-05-30 Time 10:00:00 ~ 11:00:00
Speaker Jakwang Kim Affiliation University of Wisconsin-Madison
Place Online streaming (Zoom) Streaming link ID : 688 896 1076 / PW : 54321
Topic Adversarial robustness vie optimal transport theory
Contents We study a family of adversarial multiclass classification problems and provide equivalent reformulations in terms of: 1) a family of generalized barycenter problems introduced in the paper and 2) a family of multimarginal optimal transport problems where the number of marginals is equal to the number of classes in the original classification problem. These new theoretical results reveal a rich geometric structure of adversarial learning problems in multiclass classification and extend recent results restricted to the binary classification setting. A direct computational implication of our results is that by solving either the barycenter problem and its dual, or the MOT problem and its dual, we can recover the optimal robust classification rule and the optimal adversarial strategy for the original adversarial problem. Furthermore, we prove the existence of Borel measurable robust classifiers while previous works only argue universally measurable robust classifiers only in the binary setting. Also, based on our theoretical results, we propose two new numerics relying on the truncation of the order of interactions which are faster than the state-of-art MOT algorithm in real data sets by providing empirical results using MNIST and CIFAR-10 data.
MinDS MinDS · 2023-05-25 13:26 · Views 475

POSTECH SIAM Student Chapter

🌟 DACON Ranker Special Lecture: Winning Strategies for AI Competitions 🌟

2023 POSTECH & Peking SIAM Student Chapter Joint Conference

2023 PSSC Summer Camp

2022 PSSC Summer Camp

2022 POSTECH & Peking SIAM Student Chapter Joint Conference


Information, Network & Topological Data Analysis


Recent Progress in Data Science and Applications

Fall 2021 Seminar Series

MINDS Seminar Series on Data Science, Machine Learning, and Scientific Computing

Every Tuesdays 05:00 PM


POSTECH SIAM Student Chapter Launched!