Maurice Wenig — accepted AI-conference papers

2024

Convexity Certificates for Symbolic Tensor Expressions

Paul G. Rump, Niklas Merk, Julien Klaus, Maurice Wenig, Joachim Giesen

IJCAI 2024poster

Knowing that a function is convex ensures that any local minimum is also a global minimum. Here, we implement an approach to certify the convexity of twice-differentiable functions by certifying that their second-order derivative is positive semidefinite. Both the computation of the second-order der…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Einsum Benchmark: Enabling the Development of Next-Generation Tensor Execution Engines

Mark Blacher, Christoph Staudt, Julien Klaus, Maurice Wenig, Niklas Merk, Alexander Breuer +3

NeurIPS 2024poster

Modern artificial intelligence and machine learning workflows rely on efficient tensor libraries. However, tuning tensor libraries without considering the actual problems they are meant to execute can lead to a mismatch between expected performance and the actual performance. Einsum libraries are tu…

Cited by 8 Source ↗PDF ↗Scholar ↗