Amire Bendjeddou — accepted AI-conference papers

2025

Learning Gaussian Multi-Index Models with Gradient Flow: Time Complexity and Directional Convergence

Berfin Simsek, Amire Bendjeddou, Daniel Hsu

AISTATS 2025poster

This work focuses on the gradient flow dynamics of a neural network model that uses correlation loss to approximate a multi-index function on high-dimensional standard Gaussian data. Specifically, the multi-index function we consider is a sum of neurons $f^*(x) = \sum_{j=1}^k \sigma^*(v_j^T x)$ whe…

Cited by 0 Source ↗Scholar ↗

2023

Should Under-parameterized Student Networks Copy or Average Teacher Weights?

Berfin Simsek, Amire Bendjeddou, Wulfram Gerstner, Johanni Brea

NeurIPS 2023poster

Any continuous function $f^*$ can be approximated arbitrarily well by a neural network with sufficiently many neurons $k$. We consider the case when $f^*$ itself is a neural network with one hidden layer and $k$ neurons. Approximating $f^*$ with a neural network with $n< k$ neurons can thus be seen…

Cited by 9 Source ↗PDF ↗code ↗Scholar ↗