Introduces structured DRO for learned inverse problem reconstructions with ambiguity sets aligned to the forward operator, yielding explicit dual representations and a worst-case bound that induces Tikhonov regularization on the operator Lipschitz constant.
Anal- ysis of mean-field models arising from self-attention dynamics in transformer archi- tectures with layer normalization.arXiv preprint arXiv:2501.03096
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Mean-field transformer models synchronize to a Dirac point mass exponentially fast with explicit quantitative rates under suitable parameter assumptions.
citing papers explorer
-
A Distributionally Robust Framework for Learned Reconstructions in Inverse Problems
Introduces structured DRO for learned inverse problem reconstructions with ambiguity sets aligned to the forward operator, yielding explicit dual representations and a worst-case bound that induces Tikhonov regularization on the operator Lipschitz constant.
-
Quantitative Clustering in Mean-Field Transformer Models
Mean-field transformer models synchronize to a Dirac point mass exponentially fast with explicit quantitative rates under suitable parameter assumptions.