7 citations · 11 across the 17 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2023★ 1 cited
Recovering Simultaneously Structured Data via Non-Convex Iteratively Reweighted Least Squares
Christian Kümmerle, Johannes Maly
We propose a new algorithm for the problem of recovering data that adheres to multiple, heterogeneous low-dimensional structures from linear observations. Focusing on data matrices…
cs.LG2022
A simple approach for quantizing neural networks
Johannes Maly, Rayan Saab
In this short note, we propose a new method for quantizing the weights of a fully trained neural network. A simple deterministic pre-processing step allows us to quantize network l…
cs.LG2020
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…