| |
|
| |
A monthly ML research colloquium by the New York Machine Learning Research Guild - this session in collaboration with our partner, Intuit.
The Mathematical Theory of Deep Learning
Arthur Jacot Assistant Professor, Courant Institute of Mathematical Sciences, NYU
Topic: TBD
This session is a close-quarters look at that theory, with plenty of room to push back & dig in.
About Arthur
Arthur Jacot is an Assistant Professor at NYU's Courant Institute of Mathematical Sciences. He builds mathematical theory for how deep neural networks learn, & is best known for introducing the Neural Tangent Kernel during a PhD at EPFL with Clment Hongler.
Recent work explains how DNNs act as a computational Occam's razor, finding simple, low-dimensional representations when trained with weight decay:
A proof that wide networks trained with weight decay exhibit neural collapse (ICLR 2025, oral)
An account of how DNNs break the curse of dimensionality through compositionality & symmetry learning (ICLR 2025)
A newer paper framing deep learning as a convex paradigm of computation that minimizes circuit size with ResNets
Arthur's honors include the 2025 AMR Prize in Mathematics of Artificial Intelligence & the 2023 EPFL PhD Thesis Prize.
Who this is for
NY-MLR colloquia are small by design. The room is capped, & we keep it that way so the discussion stays substantive & everyone in it can contribute.
We'd love to see you if you're:
A practitioner working seriously on ML, in industry or in a lab
A researcher or graduate student in ML, mathematics, or an adjacent field
A highly motivated student or self-directed learner of any age or background, with real depth of interest
Sincere interest is enough to belong - that's one of our core principles. What we ask is that you come ready to engage. More on the Guild & our ethos at nymlr.com.
Schedule
5:00 - 5:30 PM Doors open, arrivals, mingling
5:30 - 6:30 PM Talk
6:30 - 7:00 PM Moderated Q&A
7:00 - 8:00 PM After hours, mingling, wind-down
8:00 PM Lights out
Venue: Intuit NYC 51 Astor Pl, New York, NY 10003
Food & drinks
Food & drinks are provided - another reason to claim your seat only if you can make it, & to release it if you can't.
A note on no-shows
Seats are strictly limited by room capacity, & every in-person RSVP takes one from someone else who wanted it.
If you register to attend in person & your plans change, please amend your registration or cancel on Luma. It takes ten seconds & frees the seat.
Registering in person & not showing up without updating your RSVP will forfeit your access to future NY-MLR events. Please mark your attendance mode accurately.
A note on Unapproved Attendance
Due to limited capacity & security reasons, we will not be able to accept & accommodate unapproved drop-ins to the event, so please do not drop by uninvited as you'll be turned away by security. We apologize for the inconvenience & inability to accommodate everyone for this particular session, but please feel free to join us on our next one. Thank you for your understanding.
|
|
|
|
|
|
|
|
