3 papers
cs.IT2025
Subspace and DOA estimation under coarse quantization
Sjoerd Dirksen, Weilin Li, Johannes Maly
We study direction-of-arrival (DOA) estimation from coarsely quantized data. We focus on a two-step approach which first estimates the signal subspace via covariance estimation and…
math.PR2025
A resolution of the Gaussian hyperplane tessellation conjecture on the sphere
Sjoerd Dirksen, Nigel Q. D. Strachan
We investigate how many hyperplanes with independent standard Gaussian directions one needs to produce a -uniform tessellation of a subset of the Euclidean sphere, meaning…
stat.ML2024
Memorization With Neural Nets: Going Beyond the Worst Case
Sjoerd Dirksen, Patrick Finke, Martin Genzel
In practice, deep neural networks are often able to easily interpolate their training data. To understand this phenomenon, many works have aimed to quantify the memorization capaci…