Information Theoretic Meta Learning with Gaussian Processes
Citations
37 citations
5 citations
1 citations
References
45,034 citations
20,769 citations
11,357 citations
"Information Theoretic Meta Learning..." refers background or methods in this paper
...For all other cases where the likelihood is not Gaussian we need to construct an amortized encoding distribution by approximating each non-Gaussian likelihood term p(yt,j |ft,j), with a Gaussian term similarly to how we often parametrize a variational Bayes or Expectation-Propagation Gaussian approximation to a GP model [17, 22, 24] i....
[...]
...We first introduce some standard GP notation [24]....
[...]
...Based on the variational information bottleneck (VIB) principle [2] we introduce a new memory-based algorithm for supervised few-shot learning (right panel in Figure 1) based on Gaussian processes [24] and deep neural kernels [31] that offers a kernel-based Bayesian view of a memory system....
[...]
7,027 citations
"Information Theoretic Meta Learning..." refers background or methods in this paper
...For Augmented Omniglot we run MAML (see Appendix for the hyperparameters) since this dataset was not included in Finn et al. (2017). For additional results see Appendix D....
[...]
...Dependence on all inputs can allow to explain both transductive and non-transductive settings for meta learning (Bronskill et al., 2020; Finn et al., 2017; Nichol et al., 2018) as special cases; see Appendix B....
[...]
...Meta learning (Ravi & Larochelle, 2017; Vinyals et al., 2016; Edwards & Storkey, 2017; Finn et al., 2017; Lacoste et al., 2019; Nichol et al., 2018) and few-shot learning (Li et al....
[...]
...We recover MAML [Finn et al., 2017] as a special case of the VIB framework....
[...]
...There is a plethora of work on few-shot learning algorithms, including memory-based [Vinyals et al., 2016, Ravi and Larochelle, 2017] and gradient-based [Finn et al., 2017, Nichol et al., 2018] procedures....
[...]
5,333 citations