today local_bar

Andrei Manolache

PhD student, Universität Stuttgart

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 6

Friday, December 5, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Learning (Approximately) Equivariant Networks via Constrained Optimization

#3701 · Andrei Manolache, Luiz F. O. Chamon, Mathias Niepert

We introduce Adaptive Constrained Equivariance, a homotopy-inspired constrained optimization apprach for training equivariant neural networks.