7 citations · 14 across the 7 of their papers we have counts for
9 papers
Flattened one-bit stochastic gradient descent: compressed distributed optimization with controlled variance
Alexander Stollenwerk, Laurent Jacques
We propose a novel algorithm for distributed stochastic gradient descent (SGD) with compressed gradient communication in the parameter-server framework. Our gradient compression te…
Fast metric embedding into the Hamming cube
Sjoerd Dirksen, Shahar Mendelson, Alexander Stollenwerk
We consider the problem of embedding a subset of into a low-dimensional Hamming cube in an almost isometric way. We construct a simple, data-oblivious, and computati…
Sharp estimates on random hyperplane tessellations
Sjoerd Dirksen, Shahar Mendelson, Alexander Stollenwerk
We study the problem of generating a hyperplane tessellation of an arbitrary set in , ensuring that the Euclidean distance between any two points corresponds to t…
The Separation Capacity of Random Neural Networks
Sjoerd Dirksen, Martin Genzel, Laurent Jacques +1
Neural networks with random weights appear in a variety of machine learning applications, most prominently as the initialization of many deep learning algorithms and as a computati…
A Unified Approach to Uniform Signal Recovery From Non-Linear Observations
Martin Genzel, Alexander Stollenwerk
Recent advances in quantized compressed sensing and high-dimensional estimation have shown that signal recovery is even feasible under strong non-linear distortions in the observat…
Binarized Johnson-Lindenstrauss embeddings
Sjoerd Dirksen, Alexander Stollenwerk
We consider the problem of encoding a set of vectors into a minimal number of bits while preserving information on their Euclidean geometry. We show that this task can be accomplis…
Quantized Compressed Sensing by Rectified Linear Units
Hans Christian Jung, Johannes Maly, Lars Palzer +1
This work is concerned with the problem of recovering high-dimensional signals which belong to a convex set of low-complexity from a small number of q…
Robust 1-Bit Compressed Sensing via Hinge Loss Minimization
Martin Genzel, Alexander Stollenwerk
This work theoretically studies the problem of estimating a structured high-dimensional signal from noisy -bit Gaussian measurements. Our recovery approac…
Fast binary embeddings with Gaussian circulant matrices: improved bounds
Sjoerd Dirksen, Alexander Stollenwerk
We consider the problem of encoding a finite set of vectors into a small number of bits while approximately retaining information on the angular distances between the vectors. By d…