Jess Sorrell
@optimistsinc.bsky.social
Assistant prof at JHU CS. Interested in theory of ML, privacy, cryptography. All cat pictures my own and do not represent the cats of my employer
You are a continual inspiration to me, I hope you know this
May 1, 2025 at 12:44 AM
You are a continual inspiration to me, I hope you know this
Also congratulations!!
March 12, 2025 at 9:44 PM
Also congratulations!!
Is this in your office, and if so, when can I come pay my respects to the norm balls?
March 12, 2025 at 9:44 PM
Is this in your office, and if so, when can I come pay my respects to the norm balls?
Oh cool! A student's been teaching me about LM benchmarks recently and might be doing her project on something related to evaluating evaluations. If you make your site public, I will def point her your way!
February 19, 2025 at 4:25 AM
Oh cool! A student's been teaching me about LM benchmarks recently and might be doing her project on something related to evaluating evaluations. If you make your site public, I will def point her your way!
My turn to ask: what class?
Also, you didn't happen to snap a white board pic, did you?
Also, you didn't happen to snap a white board pic, did you?
February 19, 2025 at 3:40 AM
My turn to ask: what class?
Also, you didn't happen to snap a white board pic, did you?
Also, you didn't happen to snap a white board pic, did you?
These are the course notes I'm borrowing heavily from adaptivedataanalysis.com
The Algorithmic Foundations of Adaptive Data Analysis
Fall 2017, Taught at Penn and BU
adaptivedataanalysis.com
February 19, 2025 at 3:22 AM
These are the course notes I'm borrowing heavily from adaptivedataanalysis.com
Theory of Replicable ML. It's a mix of topics from Aaron's and Adam Smith's course on adaptive data analysis + recent work on formal algorithmic replicability. jess-sorrell.github.io/Courses/Repl...
Theory of Replicable ML
jess-sorrell.github.io
February 19, 2025 at 3:21 AM
Theory of Replicable ML. It's a mix of topics from Aaron's and Adam Smith's course on adaptive data analysis + recent work on formal algorithmic replicability. jess-sorrell.github.io/Courses/Repl...
Your timing's great, I just showed my class Moritz's result today! (Borrowing @aaroth.bsky.social's notes.) Gonna go share your post on Canvas :)
February 19, 2025 at 2:32 AM
Your timing's great, I just showed my class Moritz's result today! (Borrowing @aaroth.bsky.social's notes.) Gonna go share your post on Canvas :)
Just started rereading IJ and the whole subsidized time thing sounds too close to real for comfort
February 3, 2025 at 8:45 PM
Just started rereading IJ and the whole subsidized time thing sounds too close to real for comfort
Oh hey, now I'm excited for these papers!
January 31, 2025 at 11:15 AM
Oh hey, now I'm excited for these papers!
I worked at coffee shops for a few years and one of the joys of the job was memorizing regulars' orders to do exactly this thing. It's fun for everyone involved, I think :)
January 31, 2025 at 5:02 AM
I worked at coffee shops for a few years and one of the joys of the job was memorizing regulars' orders to do exactly this thing. It's fun for everyone involved, I think :)
I like the balls argument! Will probably go that route next time
January 30, 2025 at 4:41 AM
I like the balls argument! Will probably go that route next time
How're you holding up?
January 25, 2025 at 1:15 PM
How're you holding up?