Posts

Website update and some news from 2021

Today I updated my website after 1 year of silence. A few things have happened during this period. First and foremost, I defended my PhD thesis, and moved to Paris for my postdoc! I also have written a couple more papers (our IntSGD paper got accepted as a spotlight for ICLR 2022), gave a few online talks (check my talk Newton on method!), and got the “Rising Star in Data Science” award. More exciting papers are going to appear soon, and I will try to update my website more actively to keep those interested posted.

Last updated on Mar 9, 2022 1 min read

41 Papers reviewed in 2020 and some thoughts on reviewing

Reflecting on 2020, I realized I spent a lot of time reviewing. I reviewed 34 conference papers, 3 journal papers and 4 workshop papers. To my surprise, Lihua Lei reviewed 48 papers, 20 of which were for journals and probably took extra time due to revisions.

Reviewing is an important part of doing a PhD and it actually helps when writing papers. However, it does not help anymore once reviewing takes more time than writing. Of course, one solution that seems to be a common choice is to spend less time on each reviewed paper but this has led to the popular joke of the notorious Reviewer #2. I plan, nevertheless, to keep spending as much time as I need for every paper. My only hope is that the overall system at ML conferences would improve in near future, lowering the load on the people involved, for example by adopting the reviewing system of ICLR.

Last updated on Feb 13, 2022 1 min read

My presentation on Random Reshuffling at the Informs Annual Meeting 2020

Today I’m presenting at the INFORMS Annual Meeting at the session “Painless Large-Scale Optimization with (Almost) Hessian-Free Acceleration”, which can be accessed here if you registered for the conference. I am covering our recent work on Random Reshuffling which has been accepted at NeurIPS 2020 as a conference paper. The session is organized by Junzi Zhang and features three more speakers: Brendan O’Donoghue, Wentao Tang and Juyong Zhang.

Last updated on Feb 13, 2022 1 min read

Paper accepted to NeurIPS

Our recent paper on SGD with data shuffling (a.k.a. Random Reshuffling) got accepted and will be presented at NeurIPS in December. As this year it is fully virtual, I will be preparing a video presentation. Stay tuned! Meanwhile, you can read it on arxiv: https://arxiv.org/abs/2006.05988

Last updated on Feb 13, 2022 1 min read

Paper accepted to NeurIPS

ICML Top Reviewer

I got selected as a top 33% ranking reviewer for ICML 2020. This came as a surprise two months after the conference took place. I am also quite happy about the reviews that I got for my papers this year. This seems to be about luck as many people have expressed their disappointment about the reviewing quality. Nevertheless, in the papers that I was reviewing there was a lot of discussion, especially on borderline papers, and I feel that the quality is (slowly) improving.

Last updated on Feb 13, 2022 1 min read

ICML Top Reviewer

I'll be a reviewer for ICLR 2021

Over the past two years, I have reviewed for NeurIPS, ICML, AAAI, UAI, and several journals. Due to the crazy number of submissions each of these conferences receives, all people with expertise should consider devoting part of their time to reviewing. This year, I’m also reviewing for ICLR, even though I haven’t submitted a single paper there. But since last year they received 2594 submissions, and taking into account the dynamics, it is very likely this year the number of submissions will be close to 4000. In that case, it seems important even people who have not previously submitted to ICLR review, given they have time.

Last updated on Feb 13, 2022 1 min read

Our session on Optimization for Deep Learning at MDS Conference

Peter Richtárik, Filip Hanzely and I are organizing a session on Optimization for Deep Learning at the SIAM Conference on Mathematics of Datascience (MDS20). See the link below for more info: https://www.siam.org/conferences/cm/conference/mds20

Our presenters are:

Simon Shaolei Du from the Institute for Advanced Study of Princeton (http://simonshaoleidu.com/)

Haihao Lu from Google Research NYC (http://web.mit.edu/haihao/www/)

Sai Praneeth Karimireddy from EPFL (https://people.epfl.ch/sai.karimireddy)

Filip Hanzely from KAUST (https://fhanzely.github.io/)

Last updated on Feb 13, 2022 1 min read

Adaptive Gradient got accepted to ICML

Our work with Yura Malitsky “Adaptive Gradient Descent without Descent” got accepted at ICML with scores ‘Accept’, ‘Accept’ and ‘Weak Accept’. You can see the arxiv version of the paper here: https://arxiv.org/abs/1910.09529. Also wait for our follow-up work that we hope to release in the next few months!

Last updated on Feb 13, 2022 1 min read

Adaptive Gradient got accepted to ICML

UAI: paper accepted (1 strong accept and 4 accepts)

This year we (Filip, Peter and I) submitted one paper to the conference on Uncertainty in Artificial Intelligence (UAI). The paper got overwhelmiingly positive feedback and will be presented virtually this summer. The current title of the paper is “99% of Distributed Optimization is a Waste of Time: The Issue and How to Fix it”, but following the reviewers’ suggestions, the title will be changed to avoid confusion about its content.

Last updated on Feb 13, 2022 1 min read

ICML reviews done

At the time when there is nothing to do, no place to travel to and no party to have fun at, reviewing papers can be a good way to kill time. I just finished my reviews for ICML, and in 2 weeks there will be another deadline, reviews for UAI. I think I have never spent so much time reviewing as with this ICML, mostly because usually there are a lot of things going on around, but not now thanks to coronavirus.

Last updated on Feb 13, 2022 1 min read

ICML reviews done