Improper Deep Kernels

By Uri Heinemann, Roi Livni, Elad Eban, Gal Elidan, Amir Globerson. 2016

10 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.

1. Wengong Jin
2. Regina Barzilay
3. Tommi S. Jaakkola
4. Tao Lei
5. José Miguel Hernández-Lobato
6. Yingzhen Li
7. Percy Liang
8. Yoshua Bengio

Citations in the corpus

• Deriving Neural Architectures from Sequence and Graph Kernels (2017, methodology): “While some prior work appeals to convex optimization through improper learning (Zhang et al., 2016; Heinemann et al., 2016) (since kernel space is larger), we use the proposed networks as building blocks in typical non-convex but flexible neural network training.”
• Variational Implicit Processes (2018, background): “(2018) showed that a deep BNN is approximately equivalent to a GP with a compositional kernel (Cho & Saul, 2009; Heinemann et al., 2016; Daniely et al., 2016; Poole et al., 2016) that mimic the deep net.”