Peter Richtarik
richtarik.bsky.social
Peter Richtarik
@richtarik.bsky.social
Professor of CS and Math @ KAUST. Interested in Optimization for Machine Learning. Federated learning guru. Likes 🏓🏋️‍♂️🎾🏐⛷️⛸️🧘‍♂️🤿🎹🎸✈️🏔️📷☀️🐈🍅🥚☕️
Reposted by Peter Richtarik
Boycotting the grocery store until they start buying an equivalent volume of groceries from me
April 7, 2025 at 3:41 PM
Top 100 NeurIPS 2024 authors in terms of # of accepted papers (kind of):

papercopilot.com/paper-list/neu…

Place 8.-14. for my Optimization and Machine Learning Lab at KAUST, Saudi Arabia

Super proud of my brilliant and hard-working team!

richtarik.org/i_team.ht
ml
February 8, 2025 at 4:45 PM
Random photo of Saudi Arabia.
February 8, 2025 at 1:21 PM
Random photo of KAUST.
February 1, 2025 at 9:07 AM
Random photo of KAUST
January 29, 2025 at 2:47 PM
Random photo of KAUST.
January 28, 2025 at 11:02 AM
A random photo of KAUST
December 15, 2024 at 2:12 PM
Random photo of KAUST
December 13, 2024 at 10:51 AM
Random photo of KAUST
December 12, 2024 at 2:36 PM
I am not attending NeurIPS this year but many of my students are!

Here are our papers; check them out!

Want to join my lab as an intern, MS/PhD student, PhD student or a postdoc? Apply here: apply.interfolio.com/105097
Plus read this, too: richtarik.org/i_join.html
December 11, 2024 at 9:46 AM
When 4 out of 5 reviews are "borderline reject", the authors are on the verge of withdrawing the paper, but then, against all odds, the only "accept" reviewer decides to champion the paper.
December 7, 2024 at 6:24 AM
true
December 7, 2024 at 4:26 AM
Random photo of KAUST
December 4, 2024 at 5:23 PM
Reposted by Peter Richtarik
*AI for Mathematics and Theoretical Computer Science*, a workshop hosted jointly by the Simons Institute for the Theory of Computing and the Simons Laufer Mathematical Sciences Institute, will be held in Berkeley at April 7-11, 2025.

simons.berkeley.edu/workshops/si...
Simons Institute for the Theory of Computing and SLMath Joint Workshop: AI for Mathematics and Theoretical Computer Science
This is an exciting time for mathematics, as new technologies for mathematical reasoning provide novel opportunities for mathematical research, communication, and discovery. Mathlib, a library of form...
simons.berkeley.edu
December 2, 2024 at 10:08 PM
Random photo of KAUST
December 3, 2024 at 9:32 AM
Reposted by Peter Richtarik
Paper: Pushing the Limits of Large Language Model Quantization via the Linearity Theorem ( arxiv.org/abs/2411.17525 )
PR to Huggingface Transformers: github.com/huggingface/...
Pushing the Limits of Large Language Model Quantization via the Linearity Theorem
Quantizing large language models has become a standard way to reduce their memory and computational costs. Typically, existing methods focus on breaking down the problem into individual layer-wise sub...
arxiv.org
December 2, 2024 at 3:24 AM
Reposted by Peter Richtarik
HIGGS - A simple data-free LLM quantization method using Hadamard rotations and MSE-optimal grids, which outperforms all prior data-free approaches such as the extremely popular NF4 quantized format.

One of the author: @richtarik.bsky.social
December 2, 2024 at 3:24 AM
Random photo of KAUST
December 1, 2024 at 2:25 PM
Random photo of KAUST.
November 30, 2024 at 2:30 PM
Reposted by Peter Richtarik
Just put together a starter pack for Deep Learning Theory. Let me know if you'd like to be included or suggest someone to add to the list!

go.bsky.app/2qnppia
November 22, 2024 at 9:35 PM
My talk on computation and communication optimal asynchronous SGD at Peking University starts in 30 minutes.
November 26, 2024 at 7:28 AM
Enjoying quality dinner at Yer-Shori (耶里夏丽), Shanghai's People Square, a couple days before my talk at the Shanghai Institute for Mathematics and Interdisciplinary Sciences (SIMIS).
November 26, 2024 at 2:50 AM
Reposted by Peter Richtarik
No one can explain stochastic gradient descent better than this panda.
a panda bear is rolling around in the grass in a zoo enclosure .
Alt: a panda bear is rolling around in the grass in a zoo enclosure .
media.tenor.com
November 24, 2024 at 3:04 PM
On my way from Beijing to Shanghai (via a 340 km/h train).

On Monday (Nov 25), I am giving a talk at The Shanghai Institute for Mathematics and Interdisciplinary Sciences (SIMIS).

Talk blurb: www.simis.cn/handling-dev...
November 23, 2024 at 4:56 AM
Hi from Yuanmingyuan Park, Beijing.
November 22, 2024 at 5:18 AM