math PhD at @EPFL working in topology, ML and comp bio
Joined July 2021
- Tweets17
- Following117
- Followers121
- Likes238
kelly maggs retweeted
We're searching for a research group leader in topological data analysis! @mpicbg @csbdresden @tudresden_de These are wonderful independent positions to start a research group in mathematics for the life sciences. Deadline is October 4th. Please share! bit.ly/3YYAU9M
kelly maggs retweeted
We’ve started recruiting independent theory postdocs that would like to collaborate with experimentalists! Deadline 19 Sept! @csbdresden @mpicbg @mpi_pks @tudresden_de
You have a background in math/physics/computer science/ML and are looking for an interdisciplinary postdoc fellowship in life science, with free choice of host groups? Then join us at the CSBD as an ELBE postdoc, application deadline is 19. September!
csbdresden.de/join-us/as-a-p…
kelly maggs retweeted
Friends, I am beyond happy! I'm starting a new position as Full Professor of #MachineLearning at the University of Fribourg @unifr 🇨🇭! With #SwissAI and many other initiatives, I am taking my research at the intersection of #geometry, #topology, and #MachineLearning to a new level 🚀. This #SwissNationalDay will thus hold an even more special meaning for me—thanks for this wonderful chance, my dear confederates!
The past few years have been a veritable roller coaster 🎢, with ups and downs. Through it all, I was sustained and supported by my family, for which I am eternally grateful.
As much as we like to believe it in academia, 'no man is an island,' and I have tons of people to thank, foremost among them my postdoctoral adviser @kmborgwardt, as well as my long-term collaborators @KrishnaswamyLab and @mrguywolf. I am also indebted to my great research group at the AIDOS Lab. Working with all of you is a pleasure! 🙏
Finally, I am grateful for the advice of my mentors and role models @stefanabauer, @mmbronstein, and @guennemann (plus many others—you know who you are).
It's time to give back now and make academia better!
PS: 🔥I'm hiring soon! 🔥Please share widely and direct any inquiries to my e-mail or DM.
kelly maggs retweeted
Code now available for Diffusion Geometry!
Try the demo notebook at github.com/Iolo-Jones/Diffus…
get this into ya folks -- instant classic
Really pleased to finally share my preprint: Diffusion Geometry
(1/4) Diffusion geometry defines Riemannian geometry for data and probability spaces!
arxiv.org/abs/2405.10858
kelly maggs retweeted
Finally published!
@tessel8it @sayanmukher
A Sheaf Theoretic Construction of Shape Space
link.springer.com/article/10…
kelly maggs retweeted
🔥Blazingly fast🔥shape classification using #geometry, #topology and #MachineLearning: Differentiable Euler Characteristic Transforms
👉Today in "Halle B #94",4:30pm CEST #ICLR2024👈
👏Outstanding work by @ErnstRoell!
📜openreview.net/forum?id=MO63…
ALT Euler Characteristic Transform
was lit to present our poster at @iclr_conf and yell about k-forms with my mate @Pseudomanifold.
thanks to all who came and chatted!
based on joint work with @CeliaHacker_ and @Pseudomanifold here: arxiv.org/abs/2312.08515
kelly maggs retweeted
No message passing, no problem 🍩
#Geometry + #Topology = ❤️ in our work on neural k-forms.
Check out the poster in "Halle B #82," starting at 1045am CEST.
Fantastic work by @kellymaggs7, @CeliaHacker_, and YT.
#ICLR2024 #MachineLearning
kelly maggs retweeted
#Geometry + #Topology = ❤️ in our work on neural k-forms.
Check out the poster in "Halle B #82," starting at 1045am CEST.
Fantastic work by @kellymaggs7, @CeliaHacker_, and YT.
#ICLR2024 #MachineLearning – at Vienna, Austria
kelly maggs retweeted
Baby #2 is due any day now, and I am too wired to do the intelligent thing (i.e., sleep).
So please join me, the wonderful @osumray, and @haharrington on a journey through some fun machine learning & representation theory.
1/11
kelly maggs retweeted
New blog post: ᴅᴏɪɴɢ ᴍʟ ʀᴇꜱᴇᴀʀᴄʜ: ɢᴀᴛᴇꜱ ᴏᴘᴇɴ, ᴄᴏᴍᴇ ᴏɴ ɪɴ!
Intended as an invitation to #MachineLearning, in particular for researchers coming from #mathematics.
(Prompted by recent discussions in a @dagstuhl seminar!)
bastian.rieck.me/blog/2024/i…
GREAT explainer on our ICLR paper with wonderful collaborators @Pseudomanifold @CeliaHacker_
just the beginning of putting the homotopy theory of k-forms and simplicial cochains into geometric deep learning💫✨
cochain complexes over R,Q are the best categories CHANGE MY MIND
🎉@iclr_conf: Simplicial Representation Learning w/ Neural k-Forms
#Geometry #MachineLearning #ICLR2024
📜openreview.net/forum?id=Djw0…
TL;DR: Learnable differential forms = ꜰᴇᴀᴛᴜʀᴇ ᴍᴀᴘꜱ for combinatorial complexes (like graphs), enabling classification + more!
🧵1/n
ALT Our paper combines differential forms and simplicial chains