Addressing Bias in Active Learning with Depth Uncertainty Networks... or Not

Autor:	Murray, Chelsea, Allingham, James U., Antorán, Javier, Hernández-Lobato, José Miguel
Rok vydání:	2021
Předmět:	Computer Science - Machine Learning Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Farquhar et al. [2021] show that correcting for active learning bias with underparameterised models leads to improved downstream performance. For overparameterised models such as NNs, however, correction leads either to decreased or unchanged performance. They suggest that this is due to an "overfitting bias" which offsets the active learning bias. We show that depth uncertainty networks operate in a low overfitting regime, much like underparameterised models. They should therefore see an increase in performance with bias correction. Surprisingly, they do not. We propose that this negative result, as well as the results Farquhar et al. [2021], can be explained via the lens of the bias-variance decomposition of generalisation error. Comment: arXiv admin note: substantial text overlap with arXiv:2112.06796
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2112.06926 Zobrazit plný text záznamu View this record from Arxiv