How Inverse Conditional Flows Can Serve as a Substitute for Distributional Regression

no code implementations • 8 May 2024 • Lucas Kook, Chris Kolb, Philipp Schiele, Daniel Dold, Marcel Arpogaus, Cornelius Fritz, Philipp F. Baumann, Philipp Kopper, Tobias Pielok, Emilio Dorigatti, David Rügamer

Neural network representations of simple models, such as linear regression, are being studied increasingly to better understand the underlying principles of deep learning algorithms.

regression Time Series +1

Multi-Objective Hyperparameter Optimization -- An Overview

no code implementations • 15 Jun 2022 • Florian Karl, Tobias Pielok, Julia Moosbauer, Florian Pfisterer, Stefan Coors, Martin Binder, Lennart Schneider, Janek Thomas, Jakob Richter, Michel Lang, Eduardo C. Garrido-Merchán, Juergen Branke, Bernd Bischl

Hyperparameter optimization constitutes a large part of typical modern machine learning workflows.

Bayesian Optimization BIG-bench Machine Learning +3

Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challenges

no code implementations • 13 Jul 2021 • Bernd Bischl, Martin Binder, Michel Lang, Tobias Pielok, Jakob Richter, Stefan Coors, Janek Thomas, Theresa Ullmann, Marc Becker, Anne-Laure Boulesteix, Difan Deng, Marius Lindauer

Most machine learning algorithms are configured by one or several hyperparameters that must be carefully chosen and often considerably impact performance.

Bayesian Optimization BIG-bench Machine Learning +2