18 citations · 43 across the 8 of their papers we have counts for
9 papers
Why Capsule Neural Networks Do Not Scale: Challenging the Dynamic Parse-Tree Assumption
Matthias Mitterreiter, Marcel Koch, Joachim Giesen +1
Capsule neural networks replace simple, scalar-valued neurons with vector-valued capsules. They are motivated by the pattern recognition system in the human brain, where complex ob…
Convexity Certificates from Hessians
Julien Klaus, Niklas Merk, Konstantin Wiedom +2
The Hessian of a differentiable convex function is positive semidefinite. Therefore, checking the Hessian of a given function is a natural approach to certify convexity. However, i…
Vectorized and performance-portable Quicksort
Mark Blacher, Joachim Giesen, Peter Sanders +1
Recent works showed that implementations of Quicksort using vector CPU instructions can outperform the non-vectorized algorithms in widespread use. However, these implementations a…
Optimization for Classical Machine Learning Problems on the GPU
Sören Laue, Mark Blacher, Joachim Giesen
Constrained optimization problems arise frequently in classical machine learning. There exist frameworks addressing constrained optimization, for instance, CVXPY and GENO. However,…
A Simple and Efficient Tensor Calculus for Machine Learning
Sören Laue, Matthias Mitterreiter, Joachim Giesen
Computing derivatives of tensor expressions, also known as tensor calculus, is a fundamental task in machine learning. A key concern is the efficiency of evaluating the expressions…
GENO -- GENeric Optimization for Classical Machine Learning
Sören Laue, Matthias Mitterreiter, Joachim Giesen
Although optimization is the longstanding algorithmic backbone of machine learning, new models still require the time-consuming implementation of new solvers. As a result, there ar…
Ising Models with Latent Conditional Gaussian Variables
Frank Nussbaum, Joachim Giesen
Ising models describe the joint probability distribution of a vector of binary feature variables. Typically, not all the variables interact with each other and one is interested in…
Distributed Convex Optimization with Many Convex Constraints
Joachim Giesen, Sören Laue
We address the problem of solving convex optimization problems with many convex constraints in a distributed setting. Our approach is based on an extension of the alternating direc…
A Combinatorial Algorithm to Compute Regularization Paths
Bernd Gärtner, Joachim Giesen, Martin Jaggi +1
For a wide variety of regularization methods, algorithms computing the entire solution path have been developed recently. Solution path algorithms do not only compute the solution…