SESaMo adds a learned random symmetry operation after a normalizing flow, with a modified training objective, reaching effective sample sizes near 1.0 on symmetric and symmetry-broken target distributions.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
SESaMo: Symmetry-Enforcing Stochastic Modulation for Normalizing Flows
SESaMo adds a learned random symmetry operation after a normalizing flow, with a modified training objective, reaching effective sample sizes near 1.0 on symmetric and symmetry-broken target distributions.