PACTran: PAC-Bayesian Metrics for Estimating the Transferability of Pretrained Models to Classification Tasks

Understand

With the increasing abundance of pretrained models in recent years, the problem of selecting the best pretrained checkpoint for a particular downstream classification task has been gaining increased attention.

• Although several methods have recently been proposed to tackle the selection problem (e.g.
• LEEP, H-score), these methods resort to applying heuristics that are not well motivated by learning theory.
• In this paper we present PACTran, a theoretically grounded family of metrics for pretrained model selection and transferability measurement.