Some Guidance of Transfer Learning Algorithm Designs From Statistical Inference Perspectives – IEEE DLT, 8 Mar 2024 11:00 AM

Room: 4127, Bldg: Earth Science Building, 2207 Main Mall, Vancouver, British Columbia, Canada, V6T1Z4

Despite the success of data driven approaches in transfer learning, the theoretical understanding of transfer learning from statistics or information theory is somewhat behind. A key challenge when conducting theoretical analyses for transfer learning problems is that the statistical correlation between source and target tasks are often unknown, and hence traditional mathematical tools in statistics... Read more