3 papers
cs.LG2026
Flat Channels to Infinity in Neural Loss Landscapes
Flavio Martinelli, Alexander Van Meegen, Berfin ÅimÅek +2
The loss landscapes of neural networks contain minima and saddle points that may be connected in flat regions or appear in isolation. We identify and characterize a special structu…
cs.LG2025
Loss Landscape of Shallow ReLU-like Neural Networks: Stationary Points, Saddle Escape, and Network Embedding
Frank Zhengqing Wu, Berfin Simsek, Francois Gaston Ged
In this paper, we study the loss landscape of one-hidden-layer neural networks with ReLU-like activation functions trained with the empirical squared loss using gradient descent (G…
cs.LG2025
Learning Gaussian Multi-Index Models with Gradient Flow: Time Complexity and Directional Convergence
Berfin ÅimÅek, 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…