Why do random forests work? They are self-regularizing adaptive smoothers

Reading the abstract alone, I have no idea whether it's talking about algorithmic trees or, like, the big brown things with small green bits.

I had the exact same reaction: biology or computers?

The only hint I can see anywhere on the page is "Statistics > Machine Learning" above the abstract title.

I really want it to be about actual biological trees being studied on the scale of forests growing with smooth edges over long periods of time, but I suspect that's not what it is about.

It's talking about these[0]

[0]https://en.wikipedia.org/wiki/Random_forest

You have to know some machine learning fundamentals to figure that out - “Random Forest” is a specific machine learning algorithm, which does not need a further explanation. To take it a step further, they should really not describe “Machine learning”, no, its not like the machine takes a book and learns, its a term.

The tree is an incredibly common data structure in computer science. Decision trees are well known. Random forests are ubiquitous in Machine Learning. Should the authors really have to dumb their paper down so people who don’t work in this domain avoid confusing it with work in arborism?

Pretty sure the guy you’re replying to was half-joking, but adding the words ‘machine learning’ in the first sentence would have cleared this up pretty simply and wouldn’t have resulted in dumbing down anything.

Jeremy Howard has a great video explaining Random Forests: https://youtu.be/blyXCk4sgEg .

There's also "Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG)"

Also, the very first sentence of the actual paper (after the abstract) is

> Random forests (Breiman, 2001) have emerged as one of the most reliable off-the-shelf supervised learning algorithms [...]

arxiv.org is overwhelmingly used for math and computer science papers, though not exclusively.

The paper will also likely be submitted to a machine learning venue.

Biological trees don’t make predictions. Second or third sentence contains the phrase “randomized tree ensembles not only make predictions.”

Even single cells are able to sense and adapt to their environment. That is to recognize and react.

> avoid confusing it with work in arborism

funny!