cs.LGOct 30, 2026

Exploring Bad Minima in Transfer Learning

Authors: Mina Remeli

Organizations: Churchill College

Abstract

Transfer learning is a highly successful learning paradigm in deep learning which leverages knowledge from one task and applies it to another. Despite its success, the necessary conditions for knowledge transfer are unclear and require further research. In this dissertation, our aim is to understand transferability a little better by answering the following question: Does good generalization on a source task necessarily imply transferability to a related target task? We hypothesize the answer is negative, and attempt to find counterexamples via adversarial attacks on the transfer learning procedure. Over three types of adversarial attacks, our empirical results show a strong relationship between generalization on the source task and transferability. These results do not rule out generalization on the source task as a sufficient condition for successful transfer.

Figures & tables

Appendix figures & tables8 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Learning with Bilevel-Minimax Optimization for Efficient and Reliable Transfer Attacks

    Aug 12, 2026Yaohua Liu, Yifan Guo, Jiaxin GaoBilevel OptimizationTransfer-Based Adversarial Attacks

  2. Information-Geometric Inverse Distillation for Enhancing Adversarial Transferability

    Feb 24, 2025Wenyuan Wu, Yuan Sun, Yingke Chen +4Transfer-Based Adversarial AttacksKnowledge Distillation

  3. What Makes Adversarial Examples Transfer Across Deepfake Detectors?

    Sep 9, 2026Rafael M. Mamede, Pedro C. Neto, Ana F. SequeiraAdversarial RobustnessDeepfake Detection