Tanimoto Random Features for Scalable Molecular Machine Learning
paper
Official version Version I consider authoritative
Summary
Scalable approximation for the Tanimoto kernel (useful for GPs on molecules).
My contribution
Initiated project, co-developed minmax random features, did writing + experiments.
Thoughts
(as of 2023-11-24)
This paper does what it says it does: provides an approximation to this kernel. I am happy that this paper made modest claims and demonstrated them, in contrast to many papers which support bold claims with shaky experiments.