9 citations · 9 across the 2 of their papers we have counts for
4 papers
Compact Language, Complex Model Shifts: How and Where Ambiguity and Underspecification Affect LLMs
Michaela Regneri, Nina Scheller, Sören Laue
We analyze how lexical ambiguity and underspecification affect language model training. We create artificial homonyms and artificial hypernyms as pseudowords and analyze the genera…
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…