2 papers
cs.LG2026
Robust Fine-Tuning from Non-Robust Pretrained Models: Mitigating Suboptimal Transfer With Epsilon-Scheduling
Jonas Ngnawé, Maxime Heuillet, Sabyasachi Sahoo +5
Fine-tuning pretrained models is a standard and effective workflow in modern machine learning. However, robust fine-tuning (RFT), which aims to simultaneously achieve adaptation to…
math.LO2024
A well-quasi-order for continuous functions
Raphaël Carroy, Yann Pequignot
We prove that continuous reducibility is a well-quasi-order on the class of continuous functions between separable metrizable spaces with analytic zero-dimensional domain. To achie…