Lightnews — Scholar-powered news

Reposted by Mahdi Haghifam

Thomas Steinke @stein.ke · 4d

I'm excited to share this paper.

It answers a question that has bugged me for a long time: Can sample-and-aggregate be made more data-efficient? The answer is yes, but at a steep price in computational efficiency. See 🧵 for more details.

Also, it was a fun opportunity to add a new coauthor. 😁

Differential Privacy @differentialprivacy.org · 6d

Privately Estimating Black-Box Statistics

Günter F. Steinke, Thomas Steinke

http://arxiv.org/abs/2510.00322

1 2 10

Reposted by Mahdi Haghifam

Pierre Alquier @pierrealquier.bsky.social · 15d

The 3rd chapter of the "post-Bayes" seminar, focused on PAC-Bayes bounds, started yesterday. I gave a very introdutory talk, which is already on Youtube.

www.youtube.com/watch?v=hT-d...

There will be 5 more talks in this chapter, see the full schedule there: postbayes.github.io/seminar/

Pierre Alquier (ESSEC) - PAC Bayes: introduction and overview

YouTube video by Post-Bayes seminar

www.youtube.com

1 7 25

Reposted by Mahdi Haghifam

Nicolas Papernot @nicolaspapernot.bsky.social · 17d

Thank you to Samsung for the AI Researcher of 2025 award! I'm privileged to collaborate with many talented students & postdoctoral fellows @utoronto.ca @vectorinstitute.ai . This would not have been possible without them!

It was a great honour to receive the award from @yoshuabengio.bsky.social !

1 1 11

Mahdi Haghifam @mahdihaghifam.bsky.social · Sep 7

You will find chapter 2 of this book interesting

Introduction to Matrix Analytic Methods in Stochastic Modeling

1

Reposted by Mahdi Haghifam

Jon Ullman @thejonullman.bsky.social · Sep 4

🚨 I am co-chairing ALT 2026 this year with Matus Telgarsky. The submission server is open so please submit your best work!

Deadline: Oct 2, 2025 AoE
Confernece: Feb 23-26, 2026 in Toronto!
Website: algorithmiclearningtheory.org/alt2026/

ALT 2026 | ALT 2026 Homepage

The 37th International Conference on Algorithmic Learning Theory

algorithmiclearningtheory.org

3 12

Reposted by Mahdi Haghifam

Clément Canonne @ccanonne.github.io · Aug 17

It took me a while, but I (finally) wrote a "short" (erm) note on the "polynomial+moments method" to prove testing or indistinguishability sample complexity lower bounds. Including the infamous Ω(k/log k) tolerant uniformity testing one.

Comments and feedback welcome!

📝 github.com/ccanonne/pro...

One framed box from the note, which states that matching enough moments of a pair of suitable univariate random variables implies a sample complexity lower bound for the yes and no instances they correspond to.

3 6 25

Reposted by Mahdi Haghifam

John Preskill @preskill.bsky.social · Aug 8

In our world of (noisy) data, error correction is everywhere, as Mary Wootters eloquently explains.
www.quantamagazine.org/how-can-math...

How Can Math Protect Our Data? | Quanta Magazine

Mary Wootters discusses how error-correcting codes work, and how they are essential for reliable communication and storage.

www.quantamagazine.org

6 23

Reposted by Mahdi Haghifam

Gautam Kamath @gautamkamath.com · May 1

I wrote a post on how to connect with people (i.e., make friends) at CS conferences. These events can be intimidating so here's some suggestions on how to navigate them

I'm late for #ICLR2025 #NAACL2025, but in time for #AISTATS2025 #ICML2025! 1/3
kamathematics.wordpress.com/2025/05/01/t...

Tips on How to Connect at Academic Conferences

I was a kinda awkward teenager. If you are a CS researcher reading this post, then chances are, you were too. How to navigate social situations and make friends is not always intuitive, and has to …

kamathematics.wordpress.com

3 19 68

Reposted by Mahdi Haghifam

Thomas Steinke @stein.ke · Apr 19

Taking α→1 gives a triangle inequality for KL divergence. This can also be proved using my favourite lemma. 😁

$Full LaTeX source: https://pastebin.com/mA6KjUJs \begin{proposition}[Triangle-like inequality for KL divergence]\label{prop:kl-triangle} Let $P$, $R$, and $Q$ be probability distributions with $P$ being absolutely continuous with respect to $R$ and $R$ being absolutely conotinuous with respect to $Q$. Let $\kappa \in (1,\infty)$. Then \[ \dr{\text{KL}}{P}{Q} \le \frac{\kappa}{\kappa-1} \dr{\text{KL}}{P}{R} + \dr{\kappa}{R}{Q}, \] where $\dr{\text{KL}}{P}{Q} := \ex{X \gets P}{\log(P(X)/Q(X)}$ denotes the KL divergence and\\$\dr{\kappa}{R}{Q} = \frac{1}{\kappa-1} \log \ex{X \gets R}{(R(X)/Q(X))^{\kappa-1}}$ denotes the R\'enyi divergence of order $\kappa$. \end{proposition}$

2 5

Mahdi Haghifam @mahdihaghifam.bsky.social · Mar 23

Is there a zoom link?

1

Reposted by Mahdi Haghifam

Thomas Steinke @stein.ke · Mar 11

Excellent post from (my former😢 colleague) Nicholas Carlini on the differences between copyright law & privacy research.

In particular, from a privacy perspective, "was training data memorized?" is a yes/no question; we aren't trying to quantify how much data was memorized beyond "some" vs "none".

What my privacy papers (don't) have to say about copyright and generative AI

My work on privacy-preserving machine learning is often cited by lawyers arguing for or against how generative AI models violate copyright. This maybe isn't the right work to be citing.

nicholas.carlini.com

2 7 22

Mahdi Haghifam @mahdihaghifam.bsky.social · Jan 26

Nice! Could you share an example of their application in probability-related problems? or other problems.

2

Reposted by Mahdi Haghifam

Maxim Raginsky @mraginsky.bsky.social · Jan 22

It’s finally out — and I got to blurb it!

2 9 95

Reposted by Mahdi Haghifam

Gautam Kamath @gautamkamath.com · Jan 2

Happy new year! Guest post on my blog by Abhradeep Thakurta, featuring his perspective on interviewing/hiring for faculty and industry research positions in CS/ML. I add some of my own comments at the end. Comments and perspectives welcome!

kamathematics.wordpress.com/2025/01/02/g...

2 15

Mahdi Haghifam @mahdihaghifam.bsky.social · Dec 11

the reviewer wants to write a summary without reading the paper and you made their job “very” difficult by not having a conclusion section.

1 2

Mahdi Haghifam @mahdihaghifam.bsky.social · Dec 11

Had a great time presenting my work at this fantastic workshop! Thanks to the organizers 🙌

Jason Hartline @jasonhartline.bsky.social · Dec 4

The 2024 Junior Theorists Workshop is Thursday (at Northwestern) and Friday (at TTIC), Dec 5-6. There is a stellar lineup of outstanding junior computer science theorists who are making the future happen. Come!!

theory.cs.northwestern.edu/junior-theor...

Junior Theorists Workshop 2024 – Northwestern CS Theory Group

theory.cs.northwestern.edu

1

Mahdi Haghifam @mahdihaghifam.bsky.social · Dec 11

I’ll be at #NeurIPS2024 this week! Looking forward to presenting my joint work with Thomas Steinke(@stein.ke) and Jon Ullman(@thejonullman.bsky.social)

NeurIPS page with video: neurips.cc/virtual/2024...

Link to arxiv: arxiv.org/abs/2406.07407

3 10

Mahdi Haghifam @mahdihaghifam.bsky.social · Nov 30

Awesome 🎩
still haven’t found a good flight, will msg you if I can be there on Wednesday🙌

1

Mahdi Haghifam @mahdihaghifam.bsky.social · Nov 28

it seems the paper is behind paywall :(
Can you tell me a bit about the results?

1 1