4 citations · 8 across the 9 of their papers we have counts for
11 papers
Compressive Sensing - Introduction and Relations to Deep Learning
Hung-Hsu Chou, Johannes Maly, Holger Rauhut
Compressive sensing predicts that sparse vectors (signals) can be recovered from a small number of linear measurements via efficient algorithms. This finding, which dates back two…
From Seeds to Semantics: Measuring Semantic Accessibility in Deterministic Diffusion Models
Wei Wei, Yizhou Zeng, Kuntian Chen +3
Diffusion models generate samples through a sequence of learned denoising steps, and recent work has studied how semantic structure appears along this sampling process. We study th…
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…
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…
Neural (Tangent Kernel) Collapse
Mariia Seleznova, Dana Weitzner, Raja Giryes +2
This work bridges two important concepts: the Neural Tangent Kernel (NTK), which captures the evolution of deep neural networks (DNNs) during training, and the Neural Collapse (NC)…
Robust Implicit Regularization via Weight Normalization
Hung-Hsu Chou, Holger Rauhut, Rachel Ward
Overparameterized models may have many interpolating solutions; implicit regularization refers to the hidden preference of a particular optimization method towards a certain interp…
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…
Gradient Descent for Deep Matrix Factorization: Dynamics and Implicit Bias towards Low Rank
Hung-Hsu Chou, Carsten Gieshoff, Johannes Maly +1
In deep learning, it is common to use more network parameters than training points. In such scenarioof over-parameterization, there are usually multiple networks that achieve zero…
Overparameterization and generalization error: weighted trigonometric interpolation
Yuege Xie, Hung-Hsu Chou, Holger Rauhut +1
Motivated by surprisingly good generalization properties of learned deep neural networks in overparameterized scenarios and by the related double descent phenomenon, this paper ana…
Optimal Correlation Estimators for Quantized Signals
Michael D. Johnson, Hung H. Chou, Carl R. Gwinn
Using a maximum-likelihood criterion, we derive optimal correlation strategies for signals with and without digitization. We assume that the signals are drawn from zero-mean Gaussi…