Risk Bounds for Transferring Representations With and Without Fine-Tuning

44 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Few-Shot Learning via Learning the Representation, Provably (2020, methodology): “Lastly, we remark that there are analyses for other representation learning schemes (Arora et al., 2019, McNamara and Balcan, 2017, Galanti et al., 2016, Alquier et al., 2016, Denevi et al., 2018).”
Generalizing from a Few Examples (2019, methodology): “rning using MAML. Estimation error E est(H,I)is bounded for meta-learning of ridge regression model with a common mean [23], and fine-tuning a given parameterθ0 learned by feedforward neural networks [73]. Apart from that, as FSL sometimes becomes domain adaptation problems, such as those mentioned ”
A No-Free-Lunch Theorem for MultiTask Learning (2020, background): “…emphasis on distributions sharing common latent substructures, both as applied to classiﬁcation (Muandet, Balduzzi and Schölkopf, 2013; McNamara and Balcan, 2017; Arora et al., 2019), or to regression settings (Jalali et al., 2010; Lounici et al., 2011; Negahban and Wainwright, 2011; Du et al.,…”