6 citations · 10 across the 10 of their papers we have counts for
6 papers · 1 filter
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…
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…
(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…
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,…
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…
Convex Geometry of ReLU-layers, Injectivity on the Ball and Local Reconstruction
Daniel Haider, Martin Ehler, Peter Balazs
The paper uses a frame-theoretic setting to study the injectivity of a ReLU-layer on the closed ball of and its non-negative part. In particular, the interplay betwe…