3 papers
cs.LG2025
Improving Equivariant Networks with Probabilistic Symmetry Breaking
Hannah Lawrence, Vasco Portilheiro, Yan Zhang +1
Equivariance encodes known symmetries into neural networks, often enhancing generalization. However, equivariant networks cannot break symmetries: the output of an equivariant netw…
stat.ML2022
A tradeoff between universality of equivariant models and learnability of symmetries
Vasco Portilheiro
We prove an impossibility result, which in the context of function learning says the following: under certain conditions, it is impossible to simultaneously learn symmetries and fu…
cs.LG2019
Representation Learning with Multisets
Vasco Portilheiro
We study the problem of learning permutation invariant representations that can capture "flexible" notions of containment. We formalize this problem via a measure theoretic definit…