3 papers
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.SD2024
Hold Me Tight: Stable Encoder-Decoder Design for Speech Enhancement
Daniel Haider, Felix Perfler, Vincent Lostanlen +2
Convolutional layers with 1-D filters are often used as frontend to encode audio signals. Unlike fixed time-frequency representations, they can adapt to the local characteristics o…
cs.LG2023
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…