career update: i'll be joining @UUtah as a cs phd student in fall 2025. i'm immensely grateful to have an invaluable support system in my family who have held me strong through difficult times, and to all my mentors who've played a crucial role in my research trajectory. (1/2)
However, our algorithms require running time that is exponential in the dimension. In a future work, we will introduce efficient algorithms for this problem, and show that even better recovery bounds are possible. This work was done with my advisor, Prof. Aditya Bhaskara. (n/n)
Excited to share that our paper "Linear Regression with Heteroskedastic Errors" has been accepted to @UncertaintyInAI! We'll be at our poster session at KIT Events, Amsterdam in August to talk more about our work. In the meantime, here is an overview. (1/n)
Our algorithms are based on a simple heuristic that takes linear combinations of the inputs with small coefficients, and reduces this problem to 1D mean estimation with dependent inputs, wherein we tackle dependency issues using Janson's concentration argument. (4/n)
I'll be speaking at #STOC2026 on AI for theory, alongside industry pioneers @WittedNote (Chief Technologist, Google), David Woodruff (CMU), @SebastienBubeck (OAI), and my friend @MarkSellke (OAI) at the very kind invitation of the organizers.
See you in Salt Lake City on 6/27!
Can AI do Theory?
Some of my friends are hosting a workshop on this topic at #STOC2026 in Salt Lake City
Speakers include Scott Aaronson, @CarinaLHong, @MarkSellke, David Woodruff, @SebastienBubeck, & Prabhakar Raghavan (@WittedNote)
Call for posters ddl: 5/29
Check it out!
Introducing Prism, a free workspace for scientists to write and collaborate on research, powered by GPT-5.2.
Available today to anyone with a ChatGPT personal account: https://t.co/9mTLAbxPdH
1/ ANNOUNCING 🎬
MARYAM: The Mirror and the Map, a feature film about Fields Medalist Maryam Mirzakhani (the first woman to win the Fields Medal).
After The Man Who Knew Infinity, writer/director Matt Brown, Manjul Bhargava & I are reuniting as associate producers.
key ingredient turns out to be fractional coverings of the dependency graph. the fractional chromatic number determines how worse we are compared to the independent case: https://t.co/COyosK23cL and https://t.co/5ILYC0xIQI.
for my own reference: a nice fact about concentration bounds is that some of the ones for independent data work just as nicely for sparse dependencies. for instance, hoeffding's inequality <-> janson's inequality. entropy methods (herbst argument) also extends nicely.
@Fuzzylogin Bijnor is where Prince Bharata (after whom our country is named) lived and played with Lions. It is also where a Navratna of Akbar, your name sake, Faiz lived.
it's 2026, and im surprised that linear regression, possibly the first algorithm every ml course teaches, is far from being well understood in many settings.
I recently spoke with someone from Gen Z who just began dating someone new
He said he will upload entire chat histories of their texts and shared photos to ChatGPT and ChatGPT will analyze the relationship, break down their relational patterns and attachment styles, and advise him how to approach the relationship going forward for optimal outcomes, even crafting exact texts for him to send back to her
And it is good at it. It’s really accurate and *incredibly* good.
According to this guy, “all his friends are doing this now”
Wow.
Thinking back to that era of my life, I remember all the uncertainty of a brand new relationship. To relieve the uncertainty, we would go to our friends to share and get advice. The entire experience was human-based
This is so much easier and more powerful than that, and the entire experience is technology-based
Still trying to wrap my mind around all the implications of this. But a few initial thoughts:
1. Anything you text or send to another person can be turned over to AI without your knowledge
2. Are any of these relationships organic? What if both parties are doing this? Is this just one Chatbot dating another Chatbot with a human facade?
3. This doesn’t bode well for the traditional dating coach or marriage therapist career path
don't want to burn any bridges (yet) in my career but there's a certain big tech company with the absolute worst attitude when it comes to professionalism/respecting a potential candidate's time. i hope to be able to speak out more.
🚨 BREAKING:
Fields medalist Terry Tao on the future of mathematics (3/3):
“I got convinced that this was the future of mathematics and I started giving interviews about this.
It's a different style of writing proofs that actually is in some ways easier to read—harder to check by humans, but you see more clearly the inputs and outputs of a proof, which traditional writing often conceals.
I think the definition of a mathematician will broaden.”
Full conversation with Math, Inc.’s @jessemhan and @jdlichtman coming soon.