Axel Böhm

Axel Böhm is a researcher at the Department of Mathematics, Faculty of Mathematics, actively contributing to fields such as Stochastic Optimization, Minimax Problems, and Convergence Analysis. His work intersects Operator Theory, Machine Learning, and Data Science, with a focus on algorithm design and computational methods.

Research and Publications

• Published 8 articles (2019–2024) on topics like Nonconvex-Concave Minimax Optimization, GAN Training using Tseng's method, and Variational Inequality Algorithms.
• Key subfields include Implicit Bias in Momentum Methods, Adaptive Step Sizes, Critical Point Analysis, and Weak Minty Solutions.

Projects

• The implicit bias of momentum and adaptive step sizes (2024–2027, active).
• Vienna Graduate School on Computational Optimization (2016–2020, completed).

Scientific Collaborations

Axel collaborates with institutions and researchers in Austria and internationally. His recent work (2022–2024) involves applications in Machine Learning and Optimization Algorithms.