Posts

Asynchronous SGD accepted at NeurIPS
Our paper on Asynchronous SGD was accepted for publication at NeurIPS 2022. Hopefully, I’ll present the paper in person in December, so feel free to drop me a message if you’re planning to attend as well.
Last updated on Sep 19, 2022 1 min read
2 new papers: Newton and adaptive gradient
We recently released two new papers that are available on arxiv as preprints. The first work considers the global convergence of regularized Newton method (short summary in this twitter thread) and the second work is about adaptive stepsizes for stochastic gradient descent.
Last updated on Aug 17, 2022 1 min read
ICML 2022: Outstanding Reviewer
I was selected among top 10% of reviewers at ICML this year.
Last updated on Aug 17, 2022 1 min read
Visiting Sebastian Stich in Germany
Between 22 June and 28 June, I visited Sebastian Stich, who works at CISPA Helmholtz Center for Information Security near Saarbrücken in Germany. We discusses new ways to solve nonconvex problems, and we already have some interesting results. Sebastian is also looking for PhD students, so if you or someone you know is looking for a good supervisor working on optimization, Sebastian should be the first person to contact!
Last updated on Jun 30, 2022 1 min read
New paper: Asynchronous SGD with arbitrary delays
My first ever optimization project was an ICML paper about an asynchronous gradient method. At the time, I was quite confused by the fact that no matter what I was doing, Asynchronous gradient descent still converged. Five years later, I can finally give an answer: Because Asynchronous SGD doesn’t care about the delays, which we proved in https://arxiv.org/abs/2206.07638 our new paper. For a short summary, you can read my twitter thread about the paper or check my slides.
Last updated on Aug 1, 2022 1 min read
I'm at attending SICO conference 12-15 June

In a few days, I am travelling to Autrans, Vercors near Grenoble for the SICO conference dedicated to the 60th birthday of Anatoli Juditsky. The conference will feature a number of speakers working on optimization and statistics. As I did my master’s thesis at the University of Grenoble, I’m really happy to go there again after having been away for almost 5 years.

On the last day of the conference, I will give a talk about a new paper on Asynchronous SGD. The work that I will present is also going to appear online quite soon.

Last updated on Jun 10, 2022 1 min read
2 papers accepted to ICML

Two of my papers got accepted for presentation at ICML:

The first of these two papers was a first-time submission and the latter was a resubmission. Earlier, we opted in to release online the reviews for the Prox RR paper from NeurIPS 2021, so the ICML reviewers could see (if they searched) that our work was previously rejected. Nevertheless, it was recommended for acceptance.
Although I’m happy about my works, I feel there is still a lot of changed required to fix the reviewing process. One thing that I’m personally waiting for is that every conference would use OpenReview instead of CMT. OpenReview give the opportunity to write individual responses to the reviewers and supports LaTeX in the editor, which are amazing things.
If your paper did not get accepted, don’t take it as a strong evidence that your work is not appreciated, it often happens to high-quality works. A good example of this is the recent revelation by Mark Schmidt on Twitter that their famous SAG paper was rejected from ICML 2012.

Last updated on Jun 10, 2022 1 min read
Highlighted Reviewer of ICLR 2022
I have been selected as a “Highlighted Reviewer of ICLR 2022”, which seems to be this-year’s version of reviewer award. All reviewers are listed on the ICLR website https://iclr.cc/Conferences/2022/Reviewers. Based on my rough estimate, about 10% of reviewers received this award.
Last updated on Apr 22, 2022 1 min read
Visiting Yurii Nesterov
I’m visiting Yurii Nesterov at Université catholique de Louvain from 14 March to 17 March.
Last updated on Mar 15, 2022 1 min read
New paper: ProxSkip, a method for federated learning
Our new paper is now available on arXiv: abstract, pdf. We present a new proximal-gradient method capable of skipping computation of the proximity operator, which we designed with applications in federated learning in mind. Specifically, when the skipped operator is the averaging of local (i.e., stored on devices) iterates, this corresponds to skipping communication with provable benefits. In fact, we show that one can accelerate the convergence in terms of communication rounds, similarly to Nesterov’s acceleration but without using any momentum. Related methods, such as Scaffold, are only proved to perform comparably to gradient descent, but not better. Nevertheless, our method, when it is specialized to federated learning, is algorithmically very similar to Scaffold, so we call it Scaffnew (any guesses why?:) ).
Also, check this twitter thread if you want to read an informal description.
Last updated on Feb 21, 2022 1 min read