Tobias Hille

Tobias Hille
Raum 0445B
Universität Kassel
Fachbereich Elektrotechnik/Informatik
Fachgebiet Wissensverarbeitung
Wilhelmshöher Allee 73
34121 Kassel
Tel.: +49 561 804-6350
Email: hille@cs.uni-kassel.de
PGP: 0x94E92D8BD068FFA0
ORCID: 0000-0001-7813-9799
Code: https://codeberg.org/thille

About Me

I am a German researcher who is interested in the theory of geometric measures and dimensionality.

Publications and Preprints

• 1.

  Hanika, T., Hille, T.: What is the intrinsic dimension of your binary data? -- and how to compute it quickly. In: CONCEPTS. pp. 97–112. Springer (2024).

  URLBibTeXEndNoteBibSonomy

  @inproceedings{hanika2024intrinsic,
  author = {Hanika, Tom and Hille, Tobias},
  booktitle = {CONCEPTS},
  keywords = {itegpub},
  pages = {97--112},
  publisher = {Springer},
  series = {Lecture Notes in Computer Science},
  title = {What is the intrinsic dimension of your binary data? -- and how to compute it quickly},
  volume = 14914,
  year = 2024
  }
  

  %0 Conference Paper
  %1 hanika2024intrinsic
  %A Hanika, Tom
  %A Hille, Tobias
  %B CONCEPTS
  %D 2024
  %I Springer
  %P 97--112
  %T What is the intrinsic dimension of your binary data? -- and how to compute it quickly
  %U http://dblp.uni-trier.de/db/conf/concepts/concepts2024.html#HanikaH24
  %V 14914
  %@ 978-3-031-67868-4
  

• 1.

  Hille, T., Stubbemann, M., Hanika, T.: Reproducibility and Geometric Intrinsic Dimensionality: An Investigation on Graph Neural Network Research. Transactions on Machine Learning Research. (2024).

  URLBibTeXEndNoteBibSonomy

  @article{hille2024reproducibility,
  author = {Hille, Tobias and Stubbemann, Maximilian and Hanika, Tom},
  journal = {Transactions on Machine Learning Research},
  keywords = {itegpub},
  note = {Reproducibility Certification},
  title = {Reproducibility and Geometric Intrinsic Dimensionality: An Investigation on Graph Neural Network Research.},
  year = 2024
  }
  

  %0 Journal Article
  %1 hille2024reproducibility
  %A Hille, Tobias
  %A Stubbemann, Maximilian
  %A Hanika, Tom
  %D 2024
  %J Transactions on Machine Learning Research
  %T Reproducibility and Geometric Intrinsic Dimensionality: An Investigation on Graph Neural Network Research.
  %U https://openreview.net/forum?id=CtEGxIqtud
  

• 1.

  Stubbemann, M., Hille, T., Hanika, T.: Selecting Features by their Resilience to the Curse of Dimensionality. (2023).

  BibTeXEndNoteBibSonomy

  @article{stubbemann2023selecting,
  author = {Stubbemann, Maximilian and Hille, Tobias and Hanika, Tom},
  keywords = {itegpub},
  title = {Selecting Features by their Resilience to the Curse of Dimensionality},
  year = 2023
  }
  

  %0 Journal Article
  %1 stubbemann2023selecting
  %A Stubbemann, Maximilian
  %A Hille, Tobias
  %A Hanika, Tom
  %D 2023
  %T Selecting Features by their Resilience to the Curse of Dimensionality
  

Talks

Organizing

Reviewing

Teaching

Projects

Dimension Curse Detector (2022 — today)

This project is led by Dr. Tom Hanika within the Loewe Exploration program. In this project, we investigate to which extent machine learning is influenced by the intrinsic dimensionality of data. For this, we quantify the Curse of Dimensionality which is strongly connected to the phenomenon of measure concentration. Within the project, we develop methods that allow to efficiently compute the intrinsic dimension of modern large-scale datasets.

Extracurricular Activities

Supervision of Student Internships

I supervise an annual two-week student internship at the University of Kassel
on analyzing the emerging mastodon social network (2022 — today).