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.

Bio: Haoyang Cao received her Ph.D. (2020) from the De- partment of Industrial Engineering and Operations Research at the University of California, Berkeley, under the supervision of Prof. Xin Guo. Her thesis was on mean-field games, generative adversarial networks and the interplay between them. Later she joined the Alan Turing Institute (ATI) in the UK as a machine learning in finance research associate. During her stay at ATI (2020-2022) she worked on the identifiability issue in inverse reinforcement learning jointly with Prof. Lukasz Szpruch from the University of Edinburgh and Prof. Samuel N. Cohen from the University of Oxford. She is currently a post-doctoral researcher at Centre de Mathematiques Appliquees, Ecole Polytechnique. With Prof. Mathieu Rosenbaum, she is studying the mathematical framework of transfer learning and in particular the transferability issue.

Her research interests span two major directions. The first one is about stochastic controls, stochastic differential games and mean-field games. Along this direction, she is especially interested in the modeling problems with impulse controls and singular controls. The other direction is on the study of machine learning. Her interest in machine learning was motivated by the need of developing computational tools to solve for explicit solutions to high-dimensional stochastic games. In return, her studies on stochastic controls and games enriched the theoretical understanding of many machine learning paradigms including generative adversarial networks, inverse reinforcement learning, meta learning and transfer learning. In addition, she is working on applying her skill set of stochastic analysis, modeling and machine learning techniques to applications in financial mathematics.

Meeting Recording: https://ucsb.zoom.us/rec/share/6aVYdnIQQIJXmteQPuQq3I4fzcHKQS-IIyY-zXN8NE5Eg36YIWoFMKkvJxi0SmS7.6W6bVQSzOvDnHpNM

Access Passcode: $e5.AyX1