Machine Learning and Data Science (MLDS) Unit
In the machine learning and data science (MLDS) unit, we focus on developing fundamental machine learning algorithms and solving important scientific problems using machine learning. We are currently interested in statistical modeling for high-dimensional data including kernel and deep learning models and geometric machine learning algorithms, including graph neural networks (GNN) and optimal transport problems. In addition to developing ML models, we focus on developing new machine learning methods to automatically find a new scientific discoveries from data.
Important news
- This page is not updated. Please access to the new homepage!
News
Jan/20th/2024 One paper about Greedy optimal transport has been accepted by AISTATS 2024!
Jan/17th/2024 One paper about GNN has been accepted by ICLR 2024!
Dec/14th/2023 One paper about anomaly detection has been accepted by ICASSP 2024!
Oct/25th/2023 One paper about change detection has been accepted by WACV 2024!
Oct/7th/2023 Two papers about optimal transport have been accepted by EMNLP 2023!
Sep/22nd/2023 A distributed learning paper is accepted by NeurIPS 2023!
Sep/21st/2023 Momentum tracking paper is accepted by TMLR!
Sep/11th/2023 Explainable AI paper by Mohammad is accepted by ACML!
Aug/18th/2023 Communication efficient distributed learning paper is accepted by IEEE Transactions on Signal and Information Processing over Networks!
April/8th/2023 Deep learning based feature selection paper is accepted by IJCNN 2023!
April/3rd/2023 One optimal transport application paper is accepted by IGARSS 2023!
April/1st/2023 Mohammad has joined our unit!
March/24th/2023 One paper is accepted by IEEE TNNLS!
Dec/21st/2022 The lecture video of Prof. Arora are now available here!