66 citations · 247 across the 40 of their papers we have counts for
4 papers · 1 filter
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…
CEIP: Combining Explicit and Implicit Priors for Reinforcement Learning with Demonstrations
Kai Yan, Alexander G. Schwing, Yu-Xiong Wang
Although reinforcement learning has found widespread use in dense reward settings, training autonomous agents with sparse rewards remains challenging. To address this difficulty, p…
The Curse of Low Task Diversity: On the Failure of Transfer Learning to Outperform MAML and Their Empirical Equivalence
Brando Miranda, Patrick Yu, Yu-Xiong Wang +1
Recently, it has been observed that a transfer learning solution might be all we need to solve many few-shot learning benchmarks -- thus raising important questions about when and…
Does MAML Only Work via Feature Re-use? A Data Centric Perspective
Brando Miranda, Yu-Xiong Wang, Sanmi Koyejo
Recent work has suggested that a good embedding is all we need to solve many few-shot learning benchmarks. Furthermore, other work has strongly suggested that Model Agnostic Meta-L…