Timetable for the TrustML YSS online seminars from Sep to Oct., 2022. Time (JST)Time (Your Browser)TitleSpeaker Video Link 11:00-12:00 01/09/2022 Predicting Out-of-Distribution Error with the Projection Norm:Yaodong Yu (University of California, Berkeley) Video 10:00-11:00 02/09/2022 Understanding Dataset Difficulty with V-Usable Information:Kawin Ethayarajh (Stanford University) Video 15:00-16:00 02/09/2022 On the Impact of Estimating Example Difficulty:Chirag Agarwal (Adobe) Video 9:00-10:00 06/09/2022 Understanding Probability Estimation and Noisy Label Learning: From the Early Learning Perspective:Sheng Liu (New York University) Video 9:00-10:00 16/09/2022 Provably calibrating ML classifiers without distributional assumptions:Chirag Gupta (Carnegie Mellon University) Video 10:00-11:00 16/09/2022 Humanly Certify Superhuman Classifiers:Qiongkai Xu (University of Melbourne) No video 14:30-15:30 16/09/2022 Recent Advances in Domain Adaptation and Generalization:Mahsa Baktashmotlagh (University of Queensland) Video 10:00-11:00 06/10/2022 Challenges and Opportunities in Out-of-distribution Detection:Sharon Y. Li (University of Wisconsin Madison) Video 10:00-11:00 19/10/2022 Online Adaptation to Label Distribution Shift:Ruihan Wu (Cornell University) Video 15:00-16:00 26/10/2022 A Framework of Weakly Supervised Learning by Semi-Supervised Learning: Zhuowei Wang (Commonwealth Scientific and Industrial Research Organization, Australia) Video 16:00-17:00 26/10/2022 Statistical Aspects of Trustworthy Machine Learning Nikola Konstantinov (ETH AI Center) Video 16:00-17:00 28/10/2022 Explainable Artificial Intelligence: Academic Research and Industrial Applications in Korea Jaesik Choi (KAIST) Video 11:00-12:00 31/10/2022 Toward Efficient Evaluation and Training of Adversarially Robust Neural Networks:Gaurang Sriramanan (University of Maryland) Video 14:00-15:00 31/10/2022 A Unified Perspective on Value Backup and Exploration in Monte-Carlo Tree Search:Tuan Dam (TU Darmstadt) Video