Franceschi, L; Frasconi, P; Salzo, S; Grazzi, R; Pontil, M; (2018) Bilevel Programming for Hyperparameter Optimization and Meta-Learning. In: Dy, JG and Krause, A, (eds.) Proceedings of the 25th International Conference on Machine Learning (2018). (pp. pp. 1563-1572). PMLR (Proceedings of Machine Learning Research): Stockholm.

Preview

Text franceschi18a.pdf - Published Version Download (1MB) | Preview

Abstract

We introduce a framework based on bilevel programming that unifies gradient-based hyperparameter optimization and meta-learning. We show that an approximate version of the bilevel problem can be solved by taking into explicit account the optimization dynamics for the inner objective. Depending on the specific setting, the outer variables take either the meaning of hyperparameters in a supervised learning problem or parameters of a meta-learner. We provide sufficient conditions under which solutions of the approximate problem converge to those of the exact problem. We instantiate our approach for meta-learning in the case of deep learning where representation layers are treated as hyperparameters shared across a set of training episodes. In experiments, we confirm our theoretical findings, present encouraging results for few-shot learning and contrast the bilevel approach against classical approaches for learning-to-learn.

Download activity - last month

Export as JSONCSVXML

Download activity - last 12 months

Export as XMLCSVJSON

Downloads by country - last 12 months

Export as XMLCSVJSON

Archive Staff Only

View Item