Lenz Pracher

I like working on foundational problems in machine learning, usually by looking for the simplest argument that explains what is going on. If you are thinking about something in that direction and want to collaborate, feel free to reach out.

Incoming PhD student in Physics at Stanford, where I will be working with Surya Ganguli. I recently finished my M.Sc. in Theoretical and Mathematical Physics at TUM/LMU, working on Physics of (Machine) Learning in the Rulands Group. Before that I was a working student and intern at Quantco, spent time as a visiting researcher at Harvard Mathematics and at the Hokkaido University Department of Information Science and Technology, and did my B.Sc. in Physics at TUM.

Projects

• A Spectral Theory of Grokking
  Weight Decay induces Grokking through Evolution of the Neural Tangent Kernel.
  L Pracher, P de Jong, O Liesaus, A Jeffares, S Rulands — Research Note — 2026

• From simultaneous to leader–follower play in direct reciprocity
  Foreknowledge can be very useful to finding good strategies.
  P LaPorte, L Pracher, S Pal — PNAS Nexus 5 (2), pgag005 — 2026

• Strategies of cooperation and defection in five large language models
  LLMs have certain strategic preferences.
  S Pal, A Mallela, C Hilbe, L Pracher, C Wei, F Fu, S Schnell, MA Nowak — arXiv:2601.09849 — 2026

• LOCO: Abstracting Spectral Numerical Integrators for PDEs into Neural Operators
  We can gain some performance by adjusting the Fourier Neural Operator.
  L Pracher, T Matsubara

• Evolutionary processes that resolve cooperative dilemmas
  Simple update rules can yield surprising behaviour.
  P LaPorte, S Wang, L Pracher, S Pal, M Nowak — 2025

Contact

Email: lenz.pracher"at"gmail.com