works on

From the 1 of 8 linked papers with an AI index.

activity
20242026
collaborators

8 papers

stat.ML2026

Exact Dynamics of Multi-class Stochastic Gradient Descent

Elizabeth Collins-Woodfin, Inbar Seroussi

The paper derives exact high‑dimensional dynamics for one‑pass stochastic gradient descent on multi‑class problems, expressing risk and signal overlap via deterministic ODEs and an…

stat.ML2026

High-Dimensional Private Linear Regression with Optimal Rates

Simone Bombari, Jialei Luo, Inbar Seroussi +1

Differentially private (DP) linear regression has received significant attention in the recent theoretical literature, with several approaches proposed to improve error rates. Our…

stat.ML2026

Minimax Rates for Learning Pairwise Interactions in Attention-Style Models

Shai Zucker, Xiong Wang, Fei Lu +1

We study the convergence rate of learning pairwise interactions in single-layer attention-style models, where tokens interact through a weight matrix and a nonlinear activation fun…

cs.CV2026

A Geometric Unification of Generative AI with Manifold-Probabilistic Projection Models

Leah Bar, Liron Mor Yosef, Shai Zucker +3

Most models of generative AI for images assume that images are inherently low-dimensional objects embedded within a high-dimensional space. Additionally, it is often implicitly ass…

cond-mat.dis-nn2025

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

Noa Rubin, Kirsten Fischer, Javed Lindner +5

Feature learning in neural networks is crucial for their expressive power and inductive biases, motivating various theoretical approaches. Some approaches describe network behavior…

math.ST2025

Optimal minimax rate of learning nonlocal interaction kernels

Xiong Wang, Inbar Seroussi, Fei Lu

Nonparametric estimation of nonlocal interaction kernels is crucial in various applications involving interacting particle systems. The inference challenge, situated at the nexus o…