Gaussian processes are flexible function approximators, with inductive biases controlledbyacovariancekernel.

We thank all the reviewers for their supportive and insightful comments. While kernel learning has now been1 broadly identified as important for good performance, the vast majority of approaches, while highly useful, focus2 on parametric methods that do not represent uncertainty over the values of the kernel, can be difficult to train, and3 difficult to specify inductive biases. In the camera ready, we will fix the typos and add in-text ref-33 erences to the figures we missed. Non-axis aligned methods are also possible35 with other generalizations of FFT (possibly [3]). Inthecameraready,wewillupdatethe40 figure to be on the count instead.9:

Deep learning has enabled algorithms to generate realistic images. However, accurately predicting long video sequences requires understanding long-term dependencies and remains an open challenge.

As aresult, there is aproliferation of distinct architectures and loss functions for different vision tasks.

The metric backbone of a weighted graph is the union of all-pairs shortest paths.

In human pedagogy, teachers and students can interact adaptively to maximize communication efficiency. Theteacher adjusts herteaching method fordifferent students, and the student, after getting familiar with the teacher's instruction mechanism,caninfertheteacher'sintentiontolearnfaster.