Multi-task problems are not multi-objective

1 code implementation • 14 Oct 2021 • Michael Ruchte, Josif Grabocka

These works also use Multi-Task Learning (MTL) problems to benchmark MOO algorithms treating each task as independent objective.

BIG-bench Machine Learning Multi-Task Learning

Scalable Pareto Front Approximation for Deep Multi-Objective Learning

1 code implementation • 24 Mar 2021 • Michael Ruchte, Josif Grabocka

Prior work either demand optimizing a new network for every point on the Pareto front, or induce a large overhead to the number of trainable parameters by using hyper-networks conditioned on modifiable preferences.

NASLib: A Modular and Flexible Neural Architecture Search Library

1 code implementation • 1 Jan 2021 • Michael Ruchte, Arber Zela, Julien Niklas Siems, Josif Grabocka, Frank Hutter

Neural Architecture Search (NAS) is one of the focal points for the Deep Learning community, but reproducing NAS methods is extremely challenging due to numerous low-level implementation details.

Neural Architecture Search