Florian Pfisterer

About

Florian Pfisterer is a researcher at the intersection of automated machine learning (AutoML) and evolutionary optimization. His key research areas include hyperparameter optimization, quality diversity (QD) algorithms, and benchmarking methodologies for machine learning systems. Pfisterer’s major contribution lies in bridging the gap between AutoML and QD optimization: he pioneered the use of QD techniques to generate diverse, high-performing configurations of ML models—moving beyond single best solutions to explore trade-offs between performance, resource usage, and interpretability. His most cited work, “A collection of quality diversity optimization problems derived from hyperparameter optimization of machine learning models” (2022), introduces novel benchmark problems that transform real-world AutoML challenges into standardized QD tasks, enabling reproducible comparisons across algorithms. With 3 citations, this paper is foundational for researchers seeking to apply evolutionary methods to model selection. Pfisterer’s work is notable for its practical orientation—he designs problems that mirror actual ML deployment constraints, such as memory limits or inference speed. His contributions are shaping how the community thinks about robust, diverse model portfolios, making him a rising voice in the AutoML and evolutionary computation fields.

Research Focus

Key Achievements

Top Papers

1. 1
   A collection of quality diversity optimization problems derived from hyperparameter optimization of machine learning models

   3 citations · 2022

Key Collaborators

Contact & Links