PhD student in high energy physics
Heidelberg, Germany
Joined May 2024
- Tweets13
- Following96
- Followers73
- Likes43
Pinned Tweet
Excited to share the Lorentz-equivariant Geometric Algebra Transformer (L-GATr) for high-energy physics.
w/ @victorbreso @pimdehaan @jessethaler Tilman Plehn and @johannbrehmer
arxiv.org/abs/2405.14806
Jonas Spinner retweeted
Can transformers learn the universal pattern of jet radiation and extrapolate beyond training data?
Preprint
'Extrapolating Jet Radiation with Autoregressive Transformers' in
arxiv.org/abs/2412.12074
w @jonas_spinner, Ayo Ore, François Charton, Anja Butter and Tilman Plehn
1/7
For the first time, we have trained a Lorentz-equivariant architecture on a real-world tagging dataset (JetClass = 100M events). We find the hierarchy GNN < transformer < Lorentz-equivariant transformer, showing that equivariance also matters at scale.
5/7
We train continuous normalizing flows with Riemannian flow matching and several choices for the vector field architecture, and compare them with our autoregressive density estimator 'JetGPT'. CNFs turn out to be more data-efficient, and turning them equivariant also helps.
6/7
Thanks to the L-GATr team @victorbreso @pimdehaan Tilman Plehn Huilin Qu @jessethaler @johannbrehmer
Looking forward to exciting discussions at NeurIPS!
7/7
Thrilled to announce that L-GATr is going to NeurIPS 2024! Plus, there is a new preprint with extended experiments and a more detailed explanation.
Code: github.com/heidelberg-hepml/…
Physics paper: arxiv.org/abs/2411.00446
CS paper: arxiv.org/abs/2405.14806
1/7
To build L-GATr, we replace each transformer module with a version that processes geometric algebra objects in a Lorentz-equivariant way. Plus, there is a new operation in geometric algebra that allows for an extra layer, the geometric product.
3/7
The Lorentz-Equivariant Geometric Algebra Transformer (L-GATr) uses spacetime geometric algebra to process particles at the LHC in a Lorentz-equivariant way. We process them using a transformer architecture, combining the benefits of Lorentz and permutation equivariance.
2/7
Interested in using L-GATr (Lorentz-equivariance + geometric algebra representations + transformer) for your own high-energy physics application? Check out the L-GATr codebase at github.com/heidelberg-hepml/…
Excited to share the Lorentz-equivariant Geometric Algebra Transformer (L-GATr) for high-energy physics.
w/ @victorbreso @pimdehaan @jessethaler Tilman Plehn and @johannbrehmer
arxiv.org/abs/2405.14806
We build the (to the best of our knowledge) first Lorentz-equivariant generative network. It uses Riemannian Flow Matching (teapaw.org/RickyTQChen/status/162…) to hard-code phase space boundaries into the choice of trajectories.
Excited to share our new work on Riemannian Flow Matching.
Unlike diffusion-based approaches, it’s
- completely simulation-free on simple manifolds,
- trivially applies to higher dimensions,
- tractably generalizes to general geometries!
arxiv.org/abs/2302.03660
w/ @lipmanya
