papers

Publications (15)

cs.LG2023

The Asymmetric Maximum Margin Bias of Quasi-Homogeneous Neural Networks

Daniel Kunin, Atsushi Yamamura, Chao Ma +1

In this work, we explore the maximum-margin bias of quasi-homogeneous neural networks trained with gradient flow on an exponential loss and past a point of separability. We introdu…

cs.LG2025

Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks

Daniel Kunin, Giovanni Luca Marchetti, Feng Chen +5

What features neural networks learn, and how, remains an open question. In this paper, we introduce Alternating Gradient Flows (AGF), an algorithmic framework that describes the dy…

cs.LG2019

Loss Landscapes of Regularized Linear Autoencoders

Daniel Kunin, Jonathan M. Bloom, Aleksandrina Goeva +1

Autoencoders are a deep learning model for representation learning. When trained to minimize the distance between the data and its reconstruction, linear autoencoders (LAEs) learn…

cs.LG2021

Noether's Learning Dynamics: Role of Symmetry Breaking in Neural Networks

Hidenori Tanaka, Daniel Kunin

In nature, symmetry governs regularities, while symmetry breaking brings texture. In artificial neural networks, symmetry has been a central design principle to efficiently capture…

cs.LG2024

Stochastic Collapse: How Gradient Noise Attracts SGD Dynamics Towards Simpler Subnetworks

Feng Chen, Daniel Kunin, Atsushi Yamamura +1

In this work, we reveal a strong implicit bias of stochastic gradient descent (SGD) that drives overly expressive networks to much simpler subnetworks, thereby dramatically reducin…

cs.LG2024

Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning

Daniel Kunin, Allan Raventós, Clémentine Dominé +4

While the impressive performance of modern neural networks is often attributed to their capacity to efficiently extract task-relevant features from data, the mechanisms underlying…