News for hackers. Stuff that matters.
Re:Towards a Learning-Based Query Optimizer by karsinkk on Monday May 16, 2022 @12:04AM (#31393578)
While transforming the plan into vectors is interesting, I wish they'd gone into more detail about how the ML model prunes and filters the best plan. It is also not clear what attributes of a plan the corresponding vector encodes. I do not know much about Databloom, but it looks like this "Learning-Based Query Optimizer" is built for specific use-cases in a Data engineering/analytics setting(like K-means as cited in the article). It might not be a replacement for optimizers in traditional Databases.
Re:Towards a Learning-Based Query Optimizer by BenoitP on Monday May 16, 2022 @01:49PM (#31400982)
> not clear what attributes of a plan the corresponding vector encodes

Fig 5, page 4 from [1]:

> Topology Features

> Operator Features

> Data Movement Features

> Dataset Features

For a single logical plan, meaning it will vary in its length for another query. (which is a part I don't get: you learn a new model per query? Can you learn with a variable feature length?)

[1] https://conferences.computer.org/icde/2020/pdfs/ICDE2020-5ac...

Re:Towards a Learning-Based Query Optimizer by mountainriver on Sunday May 15, 2022 @06:11PM (#31391639)
This is cool, I’ve always thought db optimization would be a great place for ML