Doesn't matter, information geometry is eternal.

Ahhhhh you worked with Gavin Brown, he chimed in on the other site.

I was really sure that this was not a novel result when I wrote it.

People keep coming out of the woodwork (no pun intended) to tell me that this three-page note is behind the best work of their careers and I am blown away.

I will say, it is a very odd feeling to finally tick something off your to-do list after 12 years...satisfying, but odd.

Until one day recently, I dropped the notes into an LLM and...got the raw LaTeX right back out. In theory I could have done it myself in a few hours, but this was enough to get me over the "activation energy" to finally do it. So thank you, Frank and Gemini! (Please don't hate me, Bluesky)

So I reached out to Frank Nielsen, who helpfully pointed me to the relevant literature. I meant to set the record straight, but by this point I'd actually lost the original LaTeX for the notes, and just never had the time to rewrite them...

But then a weird thing happened...people found it anyway, and actually started citing it like it was a novel result! I guess I accidentally made the top Google result for "Bregman bias-variance" or something.

This was actually a note I wrote way back in grad school, but never published or even posted to arXiv. After proving the result, I couldn't find a prior reference, but it seemed so basic that I figured it must have been done already. So I posted it on my website and moved on.

You have time for doing things on the side?

Wacky and fun? How are you gonna get that funded?

I saw Margaret Mitchell reappear on Twitter talking about how unusable Bluesky had become for anyone in AI, even anti-AI people, and of course I'm a masochist, so...

The original reply guys.

"theophite followers: self-explanatory" LOL

You strike me as a deeply incurious person, and I feel very sorry for you.

Incorrect.

Your entire affect is one of smug certainty and dripping condescension about something that you know nothing about (namely, me and what I believe).

You know nothing about me, don't know my position on any of this, and just jump to conclusions based on perceived tribal affiliation. That's the thing. That's the bad thing to do.

You are doing it again!