2 papers
cs.LG2025
Is Pre-training Truly Better Than Meta-Learning?
Brando Miranda, Patrick Yu, Saumya Goyal +2
In the context of few-shot learning, it is currently believed that a fixed pre-trained (PT) model, along with fine-tuning the final layer during evaluation, outperforms standard me…
cs.LG2025
Exploring the Efficacy of Meta-Learning: Unveiling Superior Data Diversity Utilization of MAML Over Pre-training
Kavita Selva, Satita Vittayaareekul, Brando Miranda
Currently, data and model size dominate the narrative in the training of super-large, powerful models. However, there has been a lack of exploration on the effect of other attribut…