activity
20122025
most citedTight p-fusion frames

40 citations · 43 across the 7 of their papers we have counts for

collaborators

7 papers

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…

math.FA2025

Geodesic cycles on the Sphere: -designs and Marcinkiewicz-Zygmund Inequalities

Martin Ehler, Karlheinz Gröchenig, Clemens Karner

A geodesic cycle is a closed curve that connects finitely many points along geodesics. We study geodesic cycles on the sphere in regard to their role in equal-weight quadrature rul…

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.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,…

math.NA2024

Quantitative estimates: How well does the discrete Fourier transform approximate the Fourier transform on

Martin Ehler, Karlheinz Gröchenig, Andreas Klotz

In order to compute the Fourier transform of a function on the real line numerically, one samples on a grid and then takes the discrete Fourier transform. We derive exact e…

cs.LG2023★ 3 cited

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…

math.NA2012★ 40 cited

Tight p-fusion frames

Christine Bachoc, Martin Ehler

Fusion frames enable signal decompositions into weighted linear subspace components. For positive integers p, we introduce p-fusion frames, a sharpening of the notion of fusion fra…