Training Neural Networks is ER-complete

no code implementations • NeurIPS 2021 • Mikkel Abrahamsen, Linda Kleist, Tillmann Miltzow

Given a neural network, training data, and a threshold, finding weights for the neural network such that the total error is below the threshold is known to be NP-hard.

Training Neural Networks is $\exists\mathbb R$-complete

no code implementations • NeurIPS 2021 • Mikkel Abrahamsen, Linda Kleist, Tillmann Miltzow

Given a neural network, training data, and a threshold, it was known that it is NP-hard to find weights for the neural network such that the total error is below the threshold.

Scheduling with Machine Conflicts

no code implementations • 16 Feb 2021 • Moritz Buchem, Linda Kleist, Daniel Schmidt genannt Waldschmidt

Given a set of jobs, a set of machines, and a graph representing machine conflicts, the problem SchedulingWithMachineConflicts (SMC), asks for a conflict-free schedule of minimum makespan.

Discrete Mathematics Combinatorics