3 papers
cs.LG2024
Learning Gaussian Multi-Index Models with Gradient Flow: Time Complexity and Directional Convergence
Berfin Şimşek, Amire Bendjeddou, Daniel Hsu
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 dat…
math.CO2024
Lorentzian polynomials and the independence sequences of graphs
Amire Bendjeddou, Leonard Hardiman
We study the multivariate independence polynomials of graphs and the log-concavity of the coefficients of their univariate restrictions. Let be the operator defined on si…
cs.LG2023
Should Under-parameterized Student Networks Copy or Average Teacher Weights?
Berfin Şimşek, Amire Bendjeddou, Wulfram Gerstner +1
Any continuous function can be approximated arbitrarily well by a neural network with sufficiently many neurons . We consider the case when itself is a neural networ…