Feasibility and Transferability of Transfer Learning: A Mathematical Framework
Abstract
Transfer learning is an emerging and popular paradigm for utilizing existing knowledge from previous learning tasks to improve the performance of new ones. Despite its numerous empirical successes, theoretical analysis for transfer learning is limited. In this talk we introduce for the first time, to the best of our knowledge, a mathematical framework for the general procedure of transfer learning. Our unique reformulation of transfer learning as an optimization problem allows the analysis of its feasibility. Additionally, we propose a novel concept of transfer risk to evaluate transferability of transfer learning. At the end we will demonstrate how this framework can be embedded in both a generic image classification problem and a portfolio optimization problem to demonstrate the potential and benefits of incorporating transfer risk in the evaluation of transfer learning performance. This talk is primarily based on “Feasibility and Transferability of Transfer Learning: A Mathematical Framework” by Cao, Gu, Guo and Rosenbaum.
Watch recording ↗About the speaker
No bio is available for this talk.