Abstract | ||
---|---|---|
We study the problem of meta-learning through the lens of online convex optimization, developing a meta-algorithm bridging the gap between popular gradient-based meta-learning and classical regularization-based multi-task transfer methods. Our method is the first to simultaneously satisfy good sample efficiency guarantees in the convex setting, with generalization bounds that improve with task-similarity, while also being computationally scalable to modern deep learning architectures and the many-task setting. Despite its simplicity, the algorithm matches, up to a constant factor, a lower bound on the performance of any such parameter-transfer method under natural task similarity assumptions. We use experiments in both convex and deep learning settings to verify and demonstrate the applicability of our theory. |
Year | Venue | DocType |
---|---|---|
2019 | CoRR | Journal |
Volume | Citations | PageRank |
abs/1902.10644 | 0 | 0.34 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mikhail Khodak | 1 | 4 | 3.09 |
Maria-Florina Balcan | 2 | 1445 | 105.01 |
Talwalkar, Ameet | 3 | 1394 | 66.51 |