"The gist seems to be to use a linear regression model or feed a tensor flow model when a more complicated distribution is needed for the data and allow SIMD instructions working on top of GPUs / TPUs to speed up lookups. The speedup observed is anywhere from 40-60%.

That result looks impressive but I don't have enough context on say rebuilding a neural net on every DML operation. The equivalent operation that I can relate to on PG would be to rebalance the B-tree for DML operations.

In your opinion, would a ML model work for a table whose operations are both write and read heavy? I'd love to hear your thoughts on the paper."

https://www.postgresql.org/message-id/CAAerrx8bHiW3rgAqpoLqjhYhk7gHOrDtkE5UC9DAsv1w5FzpEw%40mail.gmail.com