collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2025

Aliasing in Convnets: A Frame-Theoretic Perspective

Daniel Haider, Vincent Lostanlen, Martin Ehler +2

Using a stride in a convolutional layer inherently introduces aliasing, which has implications for numerical stability and statistical generalization. While techniques such as the…

cs.LG2025

Optimal lower Lipschitz bounds for ReLU layers, saturation, and phase retrieval

Daniel Freeman, Daniel Haider

The injectivity of ReLU layers in neural networks, the recovery of vectors from clipped or saturated measurements, and (real) phase retrieval in allow for a similar…

cs.LG2024

Injectivity of ReLU-layers: Tools from Frame Theory

Daniel Haider, Martin Ehler, Peter Balazs

Injectivity is the defining property of a mapping that ensures no information is lost and any input can be perfectly reconstructed from its output. By performing hard thresholding,…

cs.LG2024

(Almost) Smooth Sailing: Towards Numerical Stability of Neural Networks Through Differentiable Regularization of the Condition Number

Rossen Nenov, Daniel Haider, Peter Balazs

Maintaining numerical stability in machine learning models is crucial for their reliability and performance. One approach to maintain stability of a network layer is to integrate t…

cs.LG2024

Instabilities in Convnets for Raw Audio

Daniel Haider, Vincent Lostanlen, Martin Ehler +1

What makes waveform-based deep learning so hard? Despite numerous attempts at training convolutional neural networks (convnets) for filterbank design, they often fail to outperform…