Current Group Member

Dr. Evelyn Herberg

Postdoctoral Researcher

I am a postdoctoral researcher at the Scientific Computing and Optimization group at the Interdisciplinary Center for Scientific Computing of Heidelberg University since September 2022.

Furthermore, I am a GAMM Junior and member of EMYA.

Currently, I am on maternity leave and working part time.

You can find my CV here.

Research Interests

My research mainly focuses on

  • Mathematical Machine Learning
  • Optimal Control with Partial Differential Equations
  • Adaptive Algorithms
  • Variational Discretization

Current and Upcoming Projects

Operator Learning for Optimal Control: Approximation and Statistical Theory
Start: 2025-01-01
End: 2027-12-31
Principal Investigators: Evelyn Herberg, Jakob Zech, Sven Wang
Staff: Mario Marić, Ly Duc Hoang
Funded by: DFG within the Priority Program funding scheme
Part of: Theoretical Foundations of Deep Learning (SPP 2298)

Recent Completed Projects

Latest Publications

  • Niklas Emonds, Evelyn Herberg, Martin Fungisai Gerchen, Marc Pritsch, Joshua Rocha, Vera Zamoscik, Peter Kirsch, Roland Herzog and Georgia Koppe
    A data‐driven closed‐loop control approach to drive neural state transitions for mechanistic insight
    Human Brain Mapping 47(11), 2026
    bioRxiv:2025.07.21.665992
    doi:10.1002/hbm.70600
    bibtex 
    @ARTICLE{EmondsHerbergGerchenPritschRochaZamoscikKirschHerzogKoppe:2026:1,
  AUTHOR = {Emonds, Niklas and Herberg, Evelyn and Gerchen, Martin Fungisai and Pritsch, Marc and Rocha, Joshua and Zamoscik, Vera and Kirsch, Peter and Herzog, Roland and Koppe, Georgia},
  PUBLISHER = {Wiley},
  DATE = {2026-07},
  DOI = {10.1002/hbm.70600},
  EPRINT = {2025.07.21.665992},
  EPRINTTYPE = {bioRxiv},
  JOURNALTITLE = {Human Brain Mapping},
  NUMBER = {11},
  TITLE = {A data‐driven closed‐loop control approach to drive neural state transitions for mechanistic insight},
  VOLUME = {47},
}
  • Leonie Kreis, Evelyn Herberg, Frederik Köhne, Anton Schiela and Roland Herzog
    SensLI: sensitivity-based layer insertion for residual and feedforward neural networks
    Journal of Machine Learning, 2026
    arXiv:2311.15995
    doi:10.4208/jml.251016
    bibtex 
    @ARTICLE{KreisHerbergKoehneSchielaHerzog:2026:1,
  AUTHOR = {Kreis, Leonie and Herberg, Evelyn and Köhne, Frederik and Schiela, Anton and Herzog, Roland},
  DATE = {2026-07},
  DOI = {10.4208/jml.251016},
  EPRINT = {2311.15995},
  EPRINTTYPE = {arXiv},
  JOURNALTITLE = {Journal of Machine Learning},
  TITLE = {SensLI: sensitivity-based layer insertion for residual and feedforward neural networks},
}
  • Bastian Dittrich, Evelyn Herberg, Roland Herzog and Georg Müller
    A DC-reformulation for gradient-$L^0$-constrained problems, 2025
    arXiv:2506.11917
    bibtex 
    @ONLINE{DittrichHerbergHerzogMueller:2025:1,
  AUTHOR = {Dittrich, Bastian and Herberg, Evelyn and Herzog, Roland and Müller, Georg},
  DATE = {2025-06},
  EPRINT = {2506.11917},
  EPRINTTYPE = {arXiv},
  TITLE = {A DC-reformulation for gradient-$L^0$-constrained problems},
}
  • Hannah Rickmann, Evelyn Herberg and Roland Herzog
    Global convergence of semismooth Newton methods for quadratic problems
    GAMM Archive for Students 7(1), p.14-30, 2025
    doi:10.14464/gammas.v7i1.810
    bibtex 
    @ARTICLE{RickmannHerbergHerzog:2025:1,
  AUTHOR = {Rickmann, Hannah and Herberg, Evelyn and Herzog, Roland},
  PUBLISHER = {Technische Universität Chemnitz},
  DATE = {2025-05},
  DOI = {10.14464/gammas.v7i1.810},
  JOURNALTITLE = {GAMM Archive for Students},
  NUMBER = {1},
  PAGES = {14--30},
  TITLE = {Global convergence of semismooth Newton methods for quadratic problems},
  VOLUME = {7},
}

Recent Teaching

Recent Events Organized