Tai-Danae Bradley

@math3ma

Ps. 148 • mathematician at SandboxAQ • blogger at Math3ma • visiting prof at TMU + Math3ma Institute: @math3ma_inst

math3ma.com

Joined August 2014

Following

19.4K

Followers

Replies Reposts Media

Tai-Danae Bradley
@math3ma
Jun 9
I recently had the chance to record a convo with @littmath about math and AI. It was great hearing a little about his workflow, some current best practices, and more. Excited to try out some new things myself, now!
1
Tai-Danae Bradley
@math3ma
Jul 1, 2025
Not too long ago, my collaborators and I wrote a preprint on the problem of uploading classical data onto a quantum computer, from a more mathematical (& category theoretical) perspective. I finally got around to blogging about the ideas. New series is up!
math3ma.com
What is a Good Quantum Encoding? Part 1
Over the past couple of years, I've been learning a little about the world of quantum machine learning (QML) and the sorts of things people are thinking about there. I recently gave an high-level...
1
Tai-Danae Bradley
@math3ma
Feb 1, 2025
10 years ago today, I launched the Math3ma blog. At the time, I wasn’t sure the site would resonate with anyone, but I’ve been amazed by all that’s happened over the past decade! To celebrate, here’s a new post on category theory and language models 🥳
math3ma.com
Magnitude, Enriched Categories, and LLMs
It's hard for me to believe, but Math3ma is TEN YEARS old today. My first entry was published on February 1, 2015 and is entitled "A Math Blog? Say What?" As evident from that post, I was very unsure...
10
Tai-Danae Bradley
@math3ma
Jan 16, 2025
Okay sure, here's a thread on our preprint 🧵arxiv.org/abs/2501.06662 It's a blend of two existing ideas in category theory: 1) magnitude and 2) a (generalized) metric space associated to an LLM. I'll say a little about each, and how we relate them.... 1/
Reuben Marks
@ReubenMarks5
Jan 15, 2025
Replying to @math3ma
How about a short thread 🧵 in the meantime?
1
Tai-Danae Bradley
@math3ma
Jan 15, 2025
New preprint with Juan Pablo Vigneaux! 🎉 Every LLM has a (generalized) metric space associated to it. We compute its “magnitude,” which is sort of like an Euler characteristic, and find it involves a sum Tsallis entropies. And more. A neat blend of ideas: arxiv.org/abs/2501.06662
7