5 papers
How to induce regularization in linear models: A guide to reparametrizing gradient flow
Hung-Hsu Chou, Johannes Maly, Dominik Stöger
In this work, we analyze the relation between reparametrizations of gradient flow and the induced implicit bias in linear models, which encompass various basic regression tasks. In…
Fast One-Pass Sparse Approximation of the Top Eigenvectors of Huge Approximately Low-Rank Matrices? Yes, !
Edem Boahen, Simone Brugiapaglia, Hung-Hsu Chou +2
Motivated by applications such as sparse PCA, in this paper we present provably-accurate one-pass algorithms for the sparse approximation of the top eigenvectors of extremely massi…
Latent Structure Emergence in Diffusion Models via Confidence-Based Filtering
Wei Wei, Yizhou Zeng, Kuntian Chen +3
Diffusion models rely on a high-dimensional latent space of initial noise seeds, yet it remains unclear whether this space contains sufficient structure to predict properties of th…
Get rid of your constraints and reparametrize: A study in NNLS and implicit bias
Hung-Hsu Chou, Johannes Maly, Claudio Mayrink Verdun +2
Over the past years, there has been significant interest in understanding the implicit bias of gradient descent optimization and its connection to the generalization properties of…
More is Less: Inducing Sparsity via Overparameterization
Hung-Hsu Chou, Johannes Maly, Holger Rauhut
In deep learning it is common to overparameterize neural networks, that is, to use more parameters than training samples. Quite surprisingly training the neural network via (stocha…