Skip To Main Content
Inbar Seroussi on Muck Rack

Inbar Seroussi

Israel
As seen in: Nature, Wiley Online Library
Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work. Claim your profile

Get in touch with Inbar

Contact Inbar, search articles and posts on X, monitor coverage, and track replies from one place.

Learn more about Muck Rack

Actions

Share this page

Is this you?

As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile

Articles

[2510.11789] Dimension-Free Minimax Rates for Learning Pairwise Interactions in Attention-Style Models

|
By Xiong Wang, Fei Lu, Inbar Seroussi
| arxiv.org
arXiv:2510.11789 (stat) View PDF HTML (experimental) Subjects: Machine Learning (stat.ML); Machine Learning (cs.LG); Probability (math.PR); Statistics Theory (math.ST) Cite as: arXiv:2510.11789 [stat.ML] (or arXiv:2510.11789v1 [stat.ML] for this version) https://doi.org/10.48550/arXiv.2510.11789 Submission history From: Inbar Seroussi [ view email] [v1] Mon, 13 Oct 2025 18:00:04 UTC (441 KB) Bibliographic Tools Bibliographic Explorer Toggle Bibliographic Explorer () Connected Papers Toggle...
Open in Who Shared View Duplicates (304) Issue with article?

From Kernels to Features: A Multi-Scale Adaptive Theory of Feature Learning

|
By Kirsten Fischer, David Dahmen, Inbar Seroussi, Javed Lindner
| arxiv.org
Open in Who Shared Issue with article?

Hitting the High-Dimensional Notes: An ODE for SGD learning dynamics on GLMs and multi-index models

|
By Elliot Paquette, Inbar Seroussi, Courtney Paquette
| arxiv.org
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Open in Who Shared View Duplicates (662) Issue with article?
See all 5 articles