Lightnews — Scholar-powered news

Call for Papers & Proposals - IKDD CODS 2025

Anirbit @anirbit.bsky.social · Aug 31

Today is 70th anniversary of the summer meeting at Dartmouth which officially marked the beginning of AI research 💥 Interestingly "Objective 3" in 1955 was already about having theory of neural nets. 🙂
stanford.io/2WJJJGN

stanford.io

Anirbit @anirbit.bsky.social · Aug 27

I got selected for the "Early Career Highlights" of ACM IKDD International Conference on Data Science (CODS) 2025. Looking forward to the talk at IISER, Pune in December.

www.acm.org/articles/acm...

Call for papers and proposals announced for CODS 2025 across various tracks of the conference. The next edition of the conference will be held in IISER Pune on December 17-20, 2025. Go through the det...

www.acm.org

Langevin Monte-Carlo Provably Learns Depth Two Neural Nets at Any Size and Data

Anirbit @anirbit.bsky.social · Aug 22

Why does noisy gradient-descent train neural nets? This fundamental question in ML remains unclear.

In our hugely revised draft my student @dkumar9.bsky.social gives the full proof that a form of noisy-GD, Langevin Monte-Carlo (#LMC), can learn arbitrary depth 2 nets.

arxiv.org/abs/2503.10428

In this work, we will establish that the Langevin Monte-Carlo algorithm can learn depth-2 neural nets of any size and for any data and we give non-asymptotic convergence rates for it. We achieve this ...

arxiv.org

1 2

Anirbit @anirbit.bsky.social · Aug 21

Registrations are now open for the international workshop on foundations of #AI4Science #SciML that we are hosting with Prof. Jakob Zech. In-person seats are very limited, please do register to join online 💥

drsciml.github.io/drsciml/

DRSciML

drsciml.github.io

Anirbit @anirbit.bsky.social · Aug 18

Please do get in touch if you have published paper(s) on solving singularly perturbed PDEs using neural nets. #AI4Science #SciML

Anirbit @anirbit.bsky.social · Aug 7

Anirbit @anirbit.bsky.social · Aug 7

Some luck to be hosted by a Godel Prize winner, Prof. Sebastien Pokutta, and to present our work in their group 💥 Sebastien heads this "Zuse Institute Berlin (#ZIB) " which is an amazing oasis of applied mathematics bringing together experts from different institutes in Berlin.

1 1 1

Reposted by Anirbit

Centre for AI Fundamentals - Manchester @aifunmcr.bsky.social · Aug 4

Interested in statistics? Prof Subhashis Ghoshal will be delivering the below public lecture tomorrow:

Title: Immersion posterior: Meeting Frequentist Goals under Structural Restrictions
Time: Aug 5 16:00-17:00
Abstract: www.newton.ac.uk/seminar/45562/
Livestream: www.newton.ac.uk/news/watch-l...

Anirbit @anirbit.bsky.social · Aug 2

Hello #FAU. Thanks for the quick plan to host me and letting me present our exciting mathematics of ML in infinite-dimensions, #operatorlearning. #sciML Their "Pattern Recognition Laboratory" is completing 50 years! @andreasmaier.bsky.social 💥

Anirbit @anirbit.bsky.social · Jul 24

Anirbit @anirbit.bsky.social · Jul 24

University of Manchester has a 1 year post-doc position that I am happy to support in our group if you are currently an #EPSRC funded PhD student - and have the required specialization for work in our group. Typicall we prefer candidates who have published in deep-learning theory or fluid theory.

Anirbit @anirbit.bsky.social · Jul 23

Anirbit @anirbit.bsky.social · Jul 23

#aiforscience

Anirbit @anirbit.bsky.social · Jul 23

Do mark your calendars for "DRSciML" (Dr. Scientific ML 😉) on September 9 and 10 🔥
drsciml.github.io/drsciml/
- We are hosting a 2 day international workshop on understanding scientific-ML.
- We have leading experts from around the world giving talks.
- There might be ticketing. Watch this space!

DRSciML

drsciml.github.io

2

Anirbit @anirbit.bsky.social · Jul 23

Anirbit @anirbit.bsky.social · Jul 6

Major ML journals that have come up in the recent years,

- dl.acm.org/journal/topml
- jds.acm.org
- link.springer.com/journal/44439
- academic.oup.com/rssdat
- jmlr.org/tmlr/
- data.mlr.press

No reason why these cant replace everything the current conferences are doing and most likely better.

Anirbit @anirbit.bsky.social · Jul 1

Thanks. No, AutoSGD is not going as far as delta-GClip goes. It's Theorem 4.5 is where they have any global minima convergence happening - but it uses assumptions which are not known to be true for nets. Our convergence holds for *all* nets wide enough.

Anirbit @anirbit.bsky.social · Jul 1

Do link to the paper! I can have a look and check.

Anirbit @anirbit.bsky.social · Jul 1

So, the next time you train a deep-learning model, it's probably worthwhile to have a baseline for the only provable adaptive gradient deep-learning algorithm - our delta-GClip 🙂

Anirbit @anirbit.bsky.social · Jun 29

Our "delta-GCLip" is the *only* known adaptive gradient algorithm that provably trains deep-nets AND is practically competitive. That's the message of our recently accepted #TMLR paper - and my 4th TMLR journal 🙂

openreview.net/pdf?id=ABT1X...

#optimization #deeplearningtheory

openreview.net

Anirbit @anirbit.bsky.social · Jun 29

Our insight is to introduce an intermediate form of gradient clipping that can leverage the PL* inequality of wide nets - something not known for standard clipping. Given our algorithm works for transformers maybe that points to some yet unkown algebraic property of them. #TMLR

Anirbit @anirbit.bsky.social · Jun 29

Our "delta-GCLip" is the *only* known adaptive gradient algorithm that provably trains deep-nets AND is practically competitive. That's the message of our recently accepted #TMLR paper - and my 4th TMLR journal 🙂

openreview.net/pdf?id=ABT1X...

#optimization #deeplearningtheory

openreview.net